Workflows

Choisissez AIndex selon ce que vous devez prouver.

Chaque workflow, c’est un problème, une commande à copier-coller, le chiffre de preuve derrière et le tier requis — sans feature cachée ni action MCP enfouie.

Télécharger gratuitement Voir le pilot report

180kPredicted naive contexttokens avoided before the agent reads

9.4kRequired context packstable, ordered and cache-aware

94.8%Predicted savingreported before the run starts

5 minSetup targetCodex, Claude Code, Cursor and more

Master plan coverage

Every master-plan workflow is present before the full registry.

The focused ledger keeps buyer-critical workflows, agent surfaces and enterprise controls discoverable instead of buried in the broader catalog.

Open registry

Costpreview only

Agent Cost Autopilot

Give the agent a budgeted plan before it starts reading.

Budgeted plan before the agent starts reading.

Surface: CLI, MCP context, dashboard, pilot report
Status: Pro · Beta · Pilot-grade

Contextpreview only

Context Packs

Graph-aware task packs with exact symbol anchors, deps, tests, risks and cache classes.

Graph-ranked task packs with hashes, cache classes and exact anchors.

Surface: CLI pack, MCP links, PR Pack, dashboard timeline
Status: Pro · Beta · Pilot-grade

Contextpreview only

Cache-Aware Context

Order context so prompt caching can actually hit.

Stable and volatile context are separated so cache behavior is visible.

Surface: Autopilot, benchmarks, ROI dashboard, pilot report
Status: Pro · Foundation · Foundation

Proofpreview only

Proof / ROI Dashboard

Show tokens avoided, cost saved, time saved and wasted reads.

Tokens avoided, cost saved, time saved and predicted vs observed proof.

Surface: Dashboard, Pilot PDF, pricing, procurement export
Status: Team · Beta · Pilot-grade

Wastepreview only

Loop Killer

Detect repeated reads, ignored packs and failing-test loops.

Repeated reads, ignored packs and loop recovery actions are surfaced.

Surface: CLI waste, dashboard waste table, MCP status, monitors
Status: Pro · Foundation · Foundation

Adoptionpreview only

Adoption Detector

Verify Codex, Claude Code, Cursor, Windsurf, VS Code, Zed, Copilot and Amp really call MCP.

Configured agents are checked against recent MCP usage.

Surface: Setup success, dashboard alerts, IDE sidebar, pilot report
Status: Pro · Foundation · Foundation

Searchpreview only

Deep Search

Iterative local research with evidence, citations and a stop condition.

Budgeted multi-step research returns citations and a stop condition.

Surface: CLI deep-search, MCP context, saved queries, dashboard evidence
Status: Pro · Foundation · Foundation

Scalepreview only

Sourcegraph parity

Cover the indispensable code intelligence workflows, then win on agent ROI.

Parity language is explicit while Sourcegraph-class claims stay gated.

Surface: Compare Sourcegraph, pricing, pilot report, benchmarks
Status: Team · Foundation · Foundation

Teampreview only

Team Shared Index

One team index per commit instead of every dev indexing the same repo.

One commit-addressed team index with freshness and local fallback.

Surface: Team index status, dashboard, CI, MCP status
Status: Team · Foundation · Foundation

Contextpreview only

PR Context Pack

Every PR gets provider-fetched changed files, blast radius, tests, owners and risks.

Changed files, blast radius, tests, owners and risk gate are packaged.

Surface: CI artifact, dashboard PR packs, GitHub/GitLab comment
Status: Team · Foundation · Foundation

Contextpreview only

Governed Context

RBAC, redaction, audit logs and policy filters for agent context.

RBAC, redaction, denied paths and audit exports stay visible.

Surface: Governance audit, Enterprise policy, monitors, pilot report
Status: Enterprise · Foundation · Foundation

Sales proofpreview only

Pilot Report

Generate a 30-minute report on the customer's real repos.

Buyer-ready report with baseline, examples, risks and rollout tier.

Surface: CLI pilot, PDF export, dashboard, compare pages, pricing
Status: Team · Foundation · Foundation

Costpreview only

Batch Autopilot

Plan multi-repo changes with an enterprise rollout gate before opening PRs.

Dry-run migration plan with rollout gate before PR creation.

Surface: CLI batch-autopilot, dashboard batch runs, owners, PR metadata
Status: Team · Foundation · Foundation

Signalspreview only

Insights

Saved queries, trends and monitors for smells, deprecated APIs and token waste.

Saved query snapshots become trends instead of one-off searches.

Surface: Dashboard insights, saved queries, pilot report
Status: Team · Foundation · Foundation

Signalspreview only

Monitoring

Saved queries, trends and monitors for smells, deprecated APIs and token waste.

Pattern alerts and threshold checks are explicit product surfaces.

Surface: Monitors, CI output, webhooks, governance alerts
Status: Team · Foundation · Foundation

Ownershippreview only

Ownership

Resolve owners and show what a change can break.

Likely owners and affected tests are attached to risky changes.

Surface: PR Pack, Batch Autopilot, dashboard, IDE current diff
Status: Team · Foundation · Foundation

Platformpreview only

Feature Discovery

The same structured JSON powers CLI, MCP tools and IDE sidebars.

No workflow ships as a hidden command or undocumented MCP action.

Surface: Feature registry, setup success, dashboard, docs, pricing
Status: Free · Foundation · Foundation

Adoptionpreview only

VSCode

The same structured JSON powers CLI, MCP tools and IDE sidebars.

IDE actions mirror the same registry used by CLI, MCP and web.

Surface: VS Code sidebar and command palette
Status: Free · Foundation · Foundation

Adoptionpreview only

CLI

The same structured JSON powers CLI, MCP tools and IDE sidebars.

Commands expose the same feature names, statuses and JSON contracts.

Surface: aindex features, status, context, pack and workflow commands
Status: Free · Foundation · Foundation

Adoptionpreview only

MCP

The same structured JSON powers CLI, MCP tools and IDE sidebars.

Five tools route advanced actions without schema bloat.

Surface: context, search, navigate, status and remember
Status: Free · Foundation · Foundation

Platformpreview only

Advanced Code Navigation

Architecture overview, dead code, smells, audit, duplicates, implementations, type hierarchy, map and rules in one router.

architecture, dead-code, smells, audit, duplicates, implementations, type-hierarchy, map and rules are one router.

Surface: MCP navigate, CLI, docs, dashboard, architecture overview
Status: Pro · Foundation · Foundation

Platformpreview only

Cross-Session Memory

Save and recall project observations across agent sessions instead of re-deriving them.

Observations and run outcomes persist and are recalled across sessions, stored locally.

Surface: MCP remember, CLI, docs, dashboard, agent sessions
Status: Pro · Foundation · Foundation

Scalepreview only

Batch Search Tools

Run many searches in one routed call to cut round-trips and tokens.

search action=batch groups related queries under one budget to cut round-trips.

Surface: MCP search, CLI, docs, dashboard, saved queries
Status: Pro · Foundation · Foundation

Platformpreview only

Self-Hosted & Air-Gapped

Run the whole index, context and proof stack locally with no network egress.

Local SQLite index, no-network mode and metadata-only exports prove zero egress.

Surface: Security, Enterprise policy, CLI doctor, docs, dashboard
Status: Enterprise · Foundation · Foundation

Platformpreview only

Code Graph Export

Export the code graph as SCIP/LSIF or native full-fidelity AIndex Graph (.aig).

SCIP/LSIF interop and native full-fidelity .aig export/import keep the graph portable.

Surface: CLI scip, CLI graph, docs, dashboard, interop
Status: Free · Foundation · Foundation

Platformpreview only

Auto-Wiki

Generate a deterministic, metadata-only code wiki from the live graph.

A deterministic, metadata-only code wiki is rendered from the live graph with signatures and flows but no raw source.

Surface: CLI wiki, MCP navigate, docs, dashboard, architecture overview
Status: Pro · Foundation · Foundation

Platformpreview only

Change Coupling

Surface files that historically change together as a git co-change blast-radius signal.

Git co-change pairs surface coupled neighbors a static dependency graph misses.

Surface: CLI context, MCP context, docs, dashboard, PR Pack
Status: Pro · Foundation · Foundation

Contextpreview only

One-Call Context Pipeline

Capsule, impact, memory recall and change-coupling in a single MCP call.

One context call returns capsule, impact, memory recall and change-coupling together.

Surface: CLI context, MCP context, docs, dashboard, agent sessions
Status: Pro · Foundation · Foundation

Reviewpreview only

Enterprise Access Control

RBAC, SSO and SCIM provisioning for enterprise teams.

RBAC, SSO and SCIM are Enterprise entitlements enforced through governance policy.

Surface: Enterprise policy, governance audit, security, pricing, docs
Status: Enterprise · Foundation · Foundation

Platformpreview only

Codebase Atlas

Understand any AI-built codebase: what it is, what it does, how it's built, what's at stake, and how it all connects.

A deterministic, metadata-only system model, drift report and ranked risk board for any AI-built repo.

Surface: CLI understand, MCP status, Studio Atlas home, dogfood page, docs
Status: Pro · Foundation · Foundation

Réduire les tokens

Faites lire moins à chaque agent avant qu’il ne dépense un token.

Budgétez la tâche, packez le plus petit contexte utile et gardez le cache de prompt chaud.

Advanced · Beta

Agent Cost Autopilot

AI coding sessions waste tokens because the first move is usually broad grep, repeated reads, and whole-file context.

aindex autopilot "fix billing login bug" --json

Turns a 180k-token naive read into a 9.4k budgeted pack before the agent spends a single token.

Advanced · Beta

Context Packs

Search results still leave agents to assemble context manually, often in the wrong order and at whole-file granularity.

aindex pack "fix checkout bug" --from-pr --json

Ships one deterministic pack per task with symbol anchors, deps, tests and a do-not-read list instead of a pile of files.

Advanced · Foundation

Cache-Aware Context

Reduced tokens are only half the cost story; unstable prompt order kills cache reuse.

aindex cache "refactor auth callbacks" --json

Orders stable repo facts first so prompt caching actually hits across agent turns.

Advanced · Foundation

Agent Loop Killer

Everyone has seen an agent read the same files again and again instead of moving forward.

aindex waste --ingest agent-session.jsonl --source codex --json

Ingests agent transcripts and flags repeated reads, ignored packs and failing-test loops with a next-call fix.

Advanced · Foundation

One-Call Context Pipeline

Agents waste round-trips chaining separate search, impact, memory and history calls before they can start editing.

aindex context "fix the checkout bug" --json

Returns capsule, impact, memory recall and change-coupling in a single MCP call instead of four round-trips.

Prouver les économies

Transformez les économies prédites en chiffres transmissibles au management.

Réconciliez prédit vs observé et exportez un pilot report prêt pour les achats.

Pro · Beta

Proof / ROI Dashboard

Token savings are hard to sell until management sees before/after proof on its own code.

aindex roi --json

Reconciles predicted vs observed token savings into an export-ready ROI board for management.

Pro · Foundation

Pilot Report

A buyer needs evidence from their own code before they trust a context optimizer.

aindex pilot --repos repo1 repo2 repo3 --pdf --json --json-output pilot-report.json

Produces a buyer-ready 30-minute report on the customer's own repos with baseline, risks and rollout tier.

Review de PR & équipe

Donnez à chaque PR et chaque équipe le même contexte.

Blast radius, tests, owners, index partagé, change coupling et monitors au même endroit.

Pro · Foundation

Team Shared Index

Teams pay cold-start cost repeatedly when each developer builds a local index in isolation.

aindex team-index sync --json && aindex team-index report --team-size 8 --json

One team index per commit replaces every developer paying the cold-start indexing cost in isolation.

Pro · Foundation

PR Context Pack

Reviewers and agents need the same high-signal context, but PR descriptions rarely include changed files, dependencies, owners, risk and test evidence.

aindex pr-pack --pr 42 --repo owner/name --provider github --output pr-pack.json --comment-output pr-comment.md --json

Every PR gets provider-fetched changed files, blast radius, owners, tests and risks as a review-ready pack.

Pro · Foundation

Batch Autopilot

Sourcegraph-style batch changes are valuable, but AI-agent teams need a simpler dry-run workflow plus explicit apply/approval/CI decisions first.

aindex batch-autopilot --query "oldApi(" --replace "newApi(" --repos all --dry-run --output aindex-batch-autopilot.json --json

Plans multi-repo changes with a dry-run rollout gate, owners and CI conclusion before any PR is opened.

Pro · Foundation

Insights & Monitoring

Teams need ongoing signals, not one-off searches buried in chat history.

aindex insights create --query oldApi --json && aindex insights snapshot --json && aindex monitors create --query sk_live_ --json && aindex monitors run --json

Turns one-off searches into saved queries, trend snapshots and live monitors for smells, deprecated APIs and token waste.

Pro · Foundation

Ownership & Blast Radius

Agents need to know who owns code and which downstream symbols/tests are affected.

aindex ownership src/auth.ts --json && aindex blast-radius --files src/auth.ts --json

Expands one changed file into callers, owners, blast radius and review routing.

Free · Foundation

Code Graph Export

Teams want to reuse the index in other tools and CI, but a code graph trapped in one tool cannot be exported or imported.

aindex graph export --out graph.aig --json && aindex scip export --out index.scip --json

Exports the index as SCIP/LSIF or native .aig so the code graph is reusable in other tools and CI.

Advanced · Foundation

Change Coupling

Static dependency graphs miss files that always change together, so agents edit one side of a coupled pair and break the other.

aindex context "touch the auth callback" --json

Surfaces files that historically change together so agents stop editing one side of a coupled pair.

Comprendre un codebase legacy

IntelliSense gratuit : references, callers, callees et definition.

Naviguez n’importe quel repo legacy ou construit par IA avec wiki de graphe, vue d’architecture et deep search.

Advanced · Foundation

Deep Search

Complex questions need more than one symbol search, but free-form search loops waste tokens.

aindex deep-search "where is session state invalidated?" --budget 12000 --json

Answers a cross-repo architecture question with cited files and a budget guard instead of an unbounded search loop.

Pro · Foundation

Sourcegraph Parity Layer

Buyers compare against Sourcegraph features even when they only need the agent-first subset.

aindex features --json

Maps Sourcegraph expectations to AiIndexer workflows and proves the agent-first wedge.

Advanced · Foundation

Advanced Code Navigation

Code intelligence beyond search lives in undocumented navigate actions, so teams never discover architecture, dead-code, duplicate and type-hierarchy analysis.

aindex blast-radius --files src/auth.ts --json

Routes architecture, dead-code, smells, duplicates, implementations and type-hierarchy through one metadata-only tool.

Advanced · Foundation

Batch Search Tools

Agents fire many one-off searches sequentially, multiplying round-trips and token cost for related lookups.

aindex search "User OR Session OR Auth" --json

Runs many related searches in one routed call to cut round-trips and tokens.

Advanced · Foundation

Auto-Wiki

New joiners and agents need an up-to-date architecture overview, but hand-written wikis go stale and raw-source dumps are unsafe to publish.

aindex wiki --include-flows --json

Generates an always-fresh, metadata-only code wiki from the live graph — never stale, never raw source.

Advanced · Foundation

Codebase Atlas

AI generates code faster than anyone can form a mental model, so teams lose track of what exists, what it does, and where the risk is.

aindex understand --json

Turns an AI-built repo into a system model, a capability-vs-claims drift report and a ranked risk board in one local run.

Gouvernance

Prouvez quel agent a demandé quel contexte — et ce qui a été refusé.

RBAC, redaction, audit, mode air-gapped et mémoire inter-sessions, gouvernés en local.

Advanced · Foundation

Agent Adoption Detector

A team can install MCP and still have agents ignore it because config, permissions or instructions are wrong.

aindex adoption --repair --json

Verifies that Codex, Claude Code, Cursor and friends actually call MCP, then emits an idempotent repair command.

Enterprise · Foundation

Governed Context

CTOs and CISOs need to know which agent requested which context and whether sensitive paths were protected.

aindex governance audit --agent Codex --team security --json && aindex governance export --limit 500 --output governance-audit-export.json --json

Gives CISOs an audit trail of which agent requested which context and whether sensitive paths were redacted.

Free · Foundation

VS Code, CLI and MCP Surfaces

Features stay hidden when they only exist as low-level commands or undocumented MCP actions.

aindex features --json && aindex status --json

The same structured JSON powers CLI, MCP tools and the IDE sidebar so features stop hiding in low-level commands.

Advanced · Foundation

Cross-Session Memory

Agents rediscover the same architecture facts every session because insights are not persisted between runs.

aindex memory search "auth uses JWT" --json

Saves and recalls project observations across sessions so agents stop re-deriving the same architecture facts.

Enterprise · Foundation

Self-Hosted & Air-Gapped

Regulated and security-sensitive teams cannot send source or metadata to a cloud and need provable local-only operation.

aindex doctor --json

Proves the full index, context and proof stack runs locally with no network egress.

Enterprise · Foundation

Enterprise Access Control

Enterprises cannot adopt a tool that lacks role-based access, single sign-on and automated user provisioning.

aindex governance policy --json

Gates RBAC, SSO and SCIM provisioning as Enterprise entitlements enforced through the governance policy surface.

Surface complète

26 workflows : contexte, preuve, review, compréhension et gouvernance.

Chaque workflow porte un problème, une commande, une action MCP, un tier, une maturité et une preuve, pour que docs, CLI, statut MCP, dashboard et marketing affichent la même vérité.

AutopilotBetapreview only

Agent Cost Autopilot

Usable for pilots, with contracts still being hardened from observed runs.

Give the agent a budgeted plan before it starts reading.

Buyer moment: The first response tells the team how much context the agent would have burned and what it should read instead.
Problem: AI coding sessions waste tokens because the first move is usually broad grep, repeated reads, and whole-file context.
Command: aindex autopilot "fix billing login bug" --json
MCP: context action=autopilot
Availability: Beta · Runnable with active hardening · Usable for pilots, with contracts still being hardened from observed runs.
Buyer grade: Pilot-grade · Buyer-safe for pilots, but still below fully hardened Sourcegraph-class parity.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Naive context, required pack, savings, risk zones, files to read, files to avoid.
Visible in: Setup success, CLI autopilot, MCP context, ROI dashboard, Pilot report
JSON proof: naive_tokens, required_pack_tokens, read_first, tests_to_run
Runtime proof: preview only

94% predicted token savings
Exact files and tests
Next MCP calls

See feature

ContextBetapreview only

Context Packs

Usable for pilots, with contracts still being hardened from observed runs.

Graph-aware task packs with exact symbol anchors, deps, tests, risks and cache classes.

Buyer moment: A task becomes a reusable artifact that agents, CI and reviewers can consume without reconstructing context.
Problem: Search results still leave agents to assemble context manually, often in the wrong order and at whole-file granularity.
Command: aindex pack "fix checkout bug" --from-pr --json
MCP: context action=pack
Availability: Beta · Runnable with active hardening · Usable for pilots, with contracts still being hardened from observed runs.
Buyer grade: Pilot-grade · Buyer-safe for pilots, but still below fully hardened Sourcegraph-class parity.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Each item carries fqn, path, line range, graph-aware reason, rank, token estimate, hash and cache class.
Visible in: CLI pack, MCP resource links, PR Pack, Dashboard timeline, Docs
JSON proof: pack_items, fqn, line_range, rank_reason, content_hash, cache_class
Runtime proof: preview only

Stable repo facts
Graph-ranked symbol pivots
Adjacent callers/dependencies
Do-not-read list

See feature

ContextFoundationpreview only

Cache-Aware Context

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Order context so prompt caching can actually hit.

Buyer moment: The buyer sees that AiIndexer reduces tokens and protects prompt-cache hit rate at the same time.
Problem: Reduced tokens are only half the cost story; unstable prompt order kills cache reuse.
Command: aindex cache "refactor auth callbacks" --json
MCP: context action=cache
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: stable_tokens, volatile_tokens and cache_hit_estimate become first-class metrics.
Visible in: CLI cache, Autopilot pack, ROI dashboard, Benchmarks, Pilot report
JSON proof: stable_tokens, volatile_tokens, cache_hit_estimate, cache_plan, stable_prefix, volatile_suffix, content_hash
Runtime proof: preview only

Stable-first ordering
Content hashes
Cache hit estimate

See feature

ProofBetapreview only

Proof / ROI Dashboard

Usable for pilots, with contracts still being hardened from observed runs.

Show tokens avoided, cost saved, time saved and wasted reads.

Buyer moment: Management gets numbers it can forward: tokens avoided, cost saved, time saved and loops killed.
Problem: Token savings are hard to sell until management sees before/after proof on its own code.
Command: aindex roi --json
MCP: status detail=roi
Availability: Beta · Runnable with active hardening · Usable for pilots, with contracts still being hardened from observed runs.
Buyer grade: Pilot-grade · Buyer-safe for pilots, but still below fully hardened Sourcegraph-class parity.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Predicted vs observed savings, top repos, top agents, loops and export-ready summary.
Visible in: Dashboard, Pilot PDF, Pricing, Team reports, Procurement export
JSON proof: tokens_avoided, cost_saved, time_saved, predicted_vs_observed
Runtime proof: preview only

ROI cards
Run timeline
PDF export

See feature

WasteFoundationpreview only

Agent Loop Killer

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Detect repeated reads, ignored packs and failing-test loops.

Buyer moment: The dashboard catches the exact behavior teams complain about: repeated reads and tests without progress.
Problem: Everyone has seen an agent read the same files again and again instead of moving forward.
Command: aindex waste --ingest agent-session.jsonl --source codex --json
MCP: status detail=waste
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Findings include ingested agent transcripts, repeated files, ignored MCP, repeated tests and suggested next calls.
Visible in: CLI waste, CLI transcript ingest, MCP status, Dashboard waste table, Pilot report, Monitors
JSON proof: loop_findings, wasted_reads, ignored_pack, ingested_events, recommended_next_call, contract_verified
Runtime proof: preview only

Loop findings
Transcript ingestion
Suggested next MCP call
Do-not-read alerts

See feature

AdoptionFoundationpreview only

Agent Adoption Detector

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Verify Codex, Claude Code, Cursor, Windsurf, VS Code, Zed, Copilot and Amp really call MCP.

Buyer moment: Install success stops being a guess because every agent is checked against real MCP usage.
Problem: A team can install MCP and still have agents ignore it because config, permissions or instructions are wrong.
Command: aindex adoption --repair --json
MCP: status detail=adoption
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Reports configured yes/no, last MCP call, likely issue and idempotent repair command.
Visible in: Setup success, CLI adoption, Dashboard alerts, Pilot report, IDE sidebar
JSON proof: agent, configured, last_mcp_call, repair_command, contract_verified
Runtime proof: preview only

Setup diagnostics
Repair command
Last MCP call

See feature

TeamFoundationpreview only

Team Shared Index

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

One team index per commit instead of every dev indexing the same repo.

Buyer moment: A CTO sees one commit-addressed index serving the team instead of every developer re-indexing locally.
Problem: Teams pay cold-start cost repeatedly when each developer builds a local index in isolation.
Command: aindex team-index sync --json && aindex team-index report --team-size 8 --json
MCP: status detail=team-index
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Fresh/stale status, commit SHA cache, team ROI report and fallback to local if the server is unavailable.
Visible in: Team index status, Dashboard, CI, MCP status, Pilot report
JSON proof: commit_sha, freshness, github_gitlab_webhooks, cache_hit_rate, duplicate_index_runs_avoided, developer_minutes_saved_estimate, local_fallback
Runtime proof: preview only

Shared cache
Auto-refresh on push
Team savings report
Fallback local

See feature

ReviewFoundationpreview only

PR Context Pack

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Every PR gets provider-fetched changed files, blast radius, tests, owners and risks.

Buyer moment: Reviewers get changed files, blast radius, tests, owners and sensitive risks before opening the diff.
Problem: Reviewers and agents need the same high-signal context, but PR descriptions rarely include changed files, dependencies, owners, risk and test evidence.
Command: aindex pr-pack --pr 42 --repo owner/name --provider github --output pr-pack.json --comment-output pr-comment.md --json
MCP: context action=pr-pack
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Metadata-only provider context from gh/glab when available, CI artifact, review gate decision and optional GitHub/GitLab comment with reviewer summary.
Visible in: CI artifact, Dashboard PR packs, GitHub/GitLab comment, MCP context, Pilot report
JSON proof: changed_files, provider_context, blast_radius, review_gate, probable_tests, owners, exports
Runtime proof: preview only

Reviewer summary
Provider-fetched changed files
Review gate decision
Probable tests
Risk zones

See feature

GovernanceFoundationpreview only

Governed Context

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

RBAC, redaction, audit logs and policy filters for agent context.

Buyer moment: Security can prove which agent asked for which context and which paths were denied or redacted.
Problem: CTOs and CISOs need to know which agent requested which context and whether sensitive paths were protected.
Command: aindex governance audit --agent Codex --team security --json && aindex governance export --limit 500 --output governance-audit-export.json --json
MCP: status detail=governance
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Audit log: agent, repo, request, pack, files, policy decision, redaction status and metadata-only export.
Visible in: Governance audit, Dashboard audit, Enterprise policy, Monitors, Pilot report
JSON proof: subject, policy_id, allowed_items, denied_items, redacted_items, hash_chain_valid, raw_payloads_included, no_cloud_source
Runtime proof: preview only

RBAC
Secret redaction
Audit exports

See feature

Sales proofFoundationpreview only

Pilot Report

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Generate a 30-minute report on the customer's real repos.

Buyer moment: Sales can prove ROI on the customer's code before procurement turns the conversation into belief.
Problem: A buyer needs evidence from their own code before they trust a context optimizer.
Command: aindex pilot --repos repo1 repo2 repo3 --pdf --json --json-output pilot-report.json
MCP: status detail=pilot
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Files, symbols, reduction estimate, risks, adoption and baseline comparison.
Visible in: CLI pilot, PDF export, Dashboard, Compare pages, Pricing
JSON proof: repos_scanned, symbols_mapped, context_reduction, recommendations, contract_verified
Runtime proof: preview only

PDF report
Baseline comparison
Pricing recommendation

See feature

SearchFoundationpreview only

Deep Search

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Iterative local research with evidence, citations and a stop condition.

Buyer moment: Complex code questions become budgeted research with citations instead of another open-ended search loop.
Problem: Complex questions need more than one symbol search, but free-form search loops waste tokens.
Command: aindex deep-search "where is session state invalidated?" --budget 12000 --json
MCP: context action=deep-search
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Steps, evidence, citations, budget used and no-loop stop condition.
Visible in: CLI deep-search, MCP context, Saved queries, Dashboard evidence, Docs
JSON proof: steps, evidence, citations, stop_condition, contract_verified
Runtime proof: preview only

File citations
Cross-repo
Budget guard

See feature

Change managementFoundationpreview only

Batch Autopilot

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Plan multi-repo changes with an enterprise rollout gate before opening PRs.

Buyer moment: Teams get Sourcegraph-style migration planning without surprise PR storms or opaque rollout cost.
Problem: Sourcegraph-style batch changes are valuable, but AI-agent teams need a simpler dry-run workflow plus explicit apply/approval/CI decisions first.
Command: aindex batch-autopilot --query "oldApi(" --replace "newApi(" --repos all --dry-run --output aindex-batch-autopilot.json --json
MCP: search action=batch
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Repos touched, candidate patches, tests, owners, risks, PR metadata and a metadata-only rollout gate with CI conclusion.
Visible in: CLI batch-autopilot, Dashboard batch runs, Owners, PR metadata, Compare Sourcegraph
JSON proof: target_repos, candidate_changes, patch_plan, owners, rollout_gate, ci_conclusion, contract_verified
Runtime proof: preview only

Patch plan
Owners
Dry-run safety
Rollout gate
Approval routing

See feature

GovernanceFoundationpreview only

Insights & Monitoring

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Saved queries, trends and monitors for smells, deprecated APIs and token waste.

Buyer moment: Saved searches become weekly signals for deprecated APIs, risky files, token waste and agent adoption.
Problem: Teams need ongoing signals, not one-off searches buried in chat history.
Command: aindex insights create --query oldApi --json && aindex insights snapshot --json && aindex monitors create --query sk_live_ --json && aindex monitors run --json
MCP: status detail=watches
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Snapshots, trends, alerts and CI/webhook output.
Visible in: Dashboard insights, Monitors, CI output, Webhook reports, Pilot report
JSON proof: saved_query, snapshot, trend, alert_status
Runtime proof: preview only

Saved queries
Trend snapshots
Monitors

See feature

ReviewFoundationpreview only

Ownership & Blast Radius

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Resolve owners and show what a change can break.

Buyer moment: Every risky change can name likely owners, downstream impact and the tests that protect it.
Problem: Agents need to know who owns code and which downstream symbols/tests are affected.
Command: aindex ownership src/auth.ts --json && aindex blast-radius --files src/auth.ts --json
MCP: navigate action=blast-radius
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: CODEOWNERS, git blame, path rules and team mapping feed PR packs and governance.
Visible in: PR Pack, Batch Autopilot, Dashboard, IDE current diff, Governance audit
JSON proof: owners, affected_symbols, dependent_files, probable_tests
Runtime proof: preview only

Owners
Reviewers
Affected tests

See feature

CompetitiveFoundationpreview only

Sourcegraph Parity Layer

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Cover the indispensable code intelligence workflows, then win on agent ROI.

Buyer moment: The buyer recognizes the enterprise checklist, then sees AiIndexer win on agent cost proof.
Problem: Buyers compare against Sourcegraph features even when they only need the agent-first subset.
Command: aindex features --json
MCP: status detail=features
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Search, navigation, Deep Search, Batch, Insights, Monitoring, Ownership, permissions and API surfaces.
Visible in: Compare Sourcegraph, Feature registry, Pricing, Pilot report, Benchmarks
JSON proof: parity_rows, wedge_rows, local_first, pricing_story, contract_verified
Runtime proof: preview only

Parity map
Local-first wedge
Simple price story

See feature

AdoptionFoundationpreview only

VS Code, CLI and MCP Surfaces

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

The same structured JSON powers CLI, MCP tools and IDE sidebars.

Buyer moment: Every feature appears where agents are actually used: setup, CLI, MCP status, dashboard and IDE.
Problem: Features stay hidden when they only exist as low-level commands or undocumented MCP actions.
Command: aindex features --json && aindex status --json
MCP: status detail=features
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Feature registry feeds docs, CLI, MCP, dashboard, setup success and VS Code sidebar.
Visible in: Setup success, CLI features, MCP status, VS Code sidebar, Docs, Command palette
JSON proof: feature_id, command, mcp_action, maturity, vscode_action
Runtime proof: preview only

Feature registry
5 MCP tools
IDE actions

See feature

NavigationFoundationpreview only

Advanced Code Navigation

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Architecture overview, dead code, smells, audit, duplicates, implementations, type hierarchy, map and rules in one router.

Buyer moment: The customer can see what problem this workflow solves and how to prove it.
Problem: Code intelligence beyond search lives in undocumented navigate actions, so teams never discover architecture, dead-code, duplicate and type-hierarchy analysis.
Command: aindex blast-radius --files src/auth.ts --json
MCP: navigate action=architecture
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: navigate routes architecture, dead-code, smells, audit, duplicates, implementations, type-hierarchy, map and rules through one metadata-only tool.
Visible in: MCP navigate, CLI blast-radius, Docs, Dashboard, Architecture overview
JSON proof: architecture, dead_code, smells, duplicates, type_hierarchy
Runtime proof: preview only

Architecture and cycle map
Dead code and smells
Type hierarchy and implementations

See feature

MemoryFoundationpreview only

Cross-Session Memory

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Save and recall project observations across agent sessions instead of re-deriving them.

Buyer moment: The customer can see what problem this workflow solves and how to prove it.
Problem: Agents rediscover the same architecture facts every session because insights are not persisted between runs.
Command: aindex memory search "auth uses JWT" --json
MCP: remember action=search
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: remember saves, searches and replays observations with run-outcome capture, all stored locally.
Visible in: MCP remember, CLI memory, Docs, Dashboard, Agent sessions
JSON proof: observation, recall_hits, history, outcome
Runtime proof: preview only

Persistent observations
Searchable recall
Run-outcome capture

See feature

SearchFoundationpreview only

Batch Search Tools

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Run many searches in one routed call to cut round-trips and tokens.

Buyer moment: The customer can see what problem this workflow solves and how to prove it.
Problem: Agents fire many one-off searches sequentially, multiplying round-trips and token cost for related lookups.
Command: aindex search "User OR Session OR Auth" --json
MCP: search action=batch
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: search action=batch groups related queries with shared ranking and a single budgeted response.
Visible in: MCP search, CLI search, Docs, Dashboard, Saved queries
JSON proof: batch_queries, grouped_results, budget_used
Runtime proof: preview only

Batched queries
Shared ranking
Fewer round-trips

See feature

DeploymentFoundationpreview only

Self-Hosted & Air-Gapped

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Run the whole index, context and proof stack locally with no network egress.

Buyer moment: The customer can see what problem this workflow solves and how to prove it.
Problem: Regulated and security-sensitive teams cannot send source or metadata to a cloud and need provable local-only operation.
Command: aindex doctor --json
MCP: status detail=full
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Local SQLite index, no-network mode, metadata-only exports and a doctor check that proves air-gapped operation.
Visible in: Security, Enterprise policy, CLI doctor, Docs, Dashboard
JSON proof: no_network, local_sqlite, egress_blocked, doctor_status
Runtime proof: preview only

No network egress
Local-only index
Air-gap doctor proof

See feature

InteropFoundationpreview only

Code Graph Export

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Export the code graph as SCIP/LSIF or native full-fidelity AIndex Graph (.aig).

Buyer moment: The customer can see what problem this workflow solves and how to prove it.
Problem: Teams want to reuse the index in other tools and CI, but a code graph trapped in one tool cannot be exported or imported.
Command: aindex graph export --out graph.aig --json && aindex scip export --out index.scip --json
MCP: status detail=features
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: scip and graph subcommands export/import SCIP/LSIF interop indexes and native .aig full-fidelity graphs.
Visible in: CLI scip, CLI graph, Docs, Dashboard, Interop
JSON proof: scip_export, aig_export, import_summary
Runtime proof: preview only

SCIP/LSIF interop
Native .aig export
Import external indexes

See feature

NavigationFoundationpreview only

Auto-Wiki

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Generate a deterministic, metadata-only code wiki from the live graph.

Buyer moment: The team gets an always-fresh, publishable architecture wiki without writing or maintaining one.
Problem: New joiners and agents need an up-to-date architecture overview, but hand-written wikis go stale and raw-source dumps are unsafe to publish.
Command: aindex wiki --include-flows --json
MCP: navigate action=map
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Index + per-module pages with signatures, structure and optional execution flows are rendered from the graph; never raw source bodies.
Visible in: CLI wiki, MCP navigate, Docs, Dashboard, Architecture overview
JSON proof: wiki_pages, module_pages, execution_flows, signatures_only, raw_source_excluded
Runtime proof: preview only

Always-fresh wiki
Metadata-only pages
Per-module flows

See feature

ReviewFoundationpreview only

Change Coupling

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Surface files that historically change together as a git co-change blast-radius signal.

Buyer moment: The agent sees the files that git history says change together before it edits one side of a coupled pair.
Problem: Static dependency graphs miss files that always change together, so agents edit one side of a coupled pair and break the other.
Command: aindex context "touch the auth callback" --json
MCP: context action=autopilot
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Git history is parsed into bounded co-change pairs and surfaced alongside pivots so the agent sees coupled neighbors before editing.
Visible in: CLI context, MCP context, Docs, Dashboard, PR Pack
JSON proof: co_changes, pair_count, focus_files, history_window
Runtime proof: preview only

Co-changed neighbors
Git history signal
Hidden blast radius

See feature

ContextFoundationpreview only

One-Call Context Pipeline

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Capsule, impact, memory recall and change-coupling in a single MCP call.

Buyer moment: One context call returns the capsule, impact, recalled insights and co-changed files, so the agent edits without round-trips.
Problem: Agents waste round-trips chaining separate search, impact, memory and history calls before they can start editing.
Command: aindex context "fix the checkout bug" --json
MCP: context task="fix the checkout bug"
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: A single context call returns the capsule, impact, prior insights (memory) and co-changed neighbors, each bounded and degrading to empty when unavailable.
Visible in: CLI context, MCP context, Docs, Dashboard, Agent sessions
JSON proof: capsule, impact, memory_recall, co_changes, next_calls
Runtime proof: preview only

One call, full pipeline
Fewer round-trips
Memory + co-change surfaced

See feature

GovernanceFoundationpreview only

Enterprise Access Control

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

RBAC, SSO and SCIM provisioning for enterprise teams.

Buyer moment: Security and IT see RBAC, SSO and SCIM gated to Enterprise and enforced through governance policy.
Problem: Enterprises cannot adopt a tool that lacks role-based access, single sign-on and automated user provisioning.
Command: aindex governance policy --json
MCP: status detail=governance
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Role-based access control, single sign-on and SCIM user provisioning are gated as Enterprise entitlements and enforced against the governance policy surface.
Visible in: Enterprise policy, Governance audit, Security, Pricing, Docs
JSON proof: rbac_roles, sso_provider, scim_provisioning, policy_decision, enterprise_plan
Runtime proof: preview only

Role-based access control
Single sign-on (SSO)
SCIM user provisioning

See feature

ComprehensionFoundationpreview only

Codebase Atlas

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Understand any AI-built codebase: what it is, what it does, how it's built, what's at stake, and how it all connects.

Buyer moment: A team that built fast with AI finally sees what the codebase is, what it does, where the risk concentrates and how it all connects.
Problem: AI generates code faster than anyone can form a mental model, so teams lose track of what exists, what it does, and where the risk is.
Command: aindex understand --json
MCP: status detail=atlas
Availability: Foundation · Foundation in place · Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.
Buyer grade: Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.
Enabled / available / observed: Enabled: yes · Available: yes · Observed: no
Proof: Atlas builds a deterministic, metadata-only model of the codebase: subsystems and their purpose, a capability-vs-claims drift report, a ranked risk board, and cross-surface traceability from one local run.
Visible in: CLI understand, MCP status, Studio Atlas home, Dogfood page, Docs
JSON proof: system_model, drift_report, risk_board, traceability, metadata_only
Runtime proof: preview only

System model of subsystems and their purpose
Capability-vs-claims drift report (undocumented and phantom)
Ranked risk board (hotspots, cycles, dead-code, untested, fragmentation)
Cross-surface traceability, metadata-only and local-first

See feature

Feature visibility checklist

Every planned feature name is visible.

Some buyer-facing names are grouped in the registry, so this checklist spells them out and ties each one back to a buyer-safe feature status.

Agent Cost AutopilotBeta

Agent Cost Autopilot

Budgeted plan before the agent starts reading.

Surface: CLI, MCP context, dashboard, pilot report
Buyer-safe status: Beta · Pilot-grade
Runtime: preview only

Context PacksBeta

Context Packs

Graph-ranked task packs with hashes, cache classes and exact anchors.

Surface: CLI pack, MCP links, PR Pack, dashboard timeline
Buyer-safe status: Beta · Pilot-grade
Runtime: preview only

Cache-Aware ContextFoundation

Cache-Aware Context

Stable and volatile context are separated so cache behavior is visible.

Surface: Autopilot, benchmarks, ROI dashboard, pilot report
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Proof / ROI DashboardBeta

Proof / ROI Dashboard

Tokens avoided, cost saved, time saved and predicted vs observed proof.

Surface: Dashboard, Pilot PDF, pricing, procurement export
Buyer-safe status: Beta · Pilot-grade
Runtime: preview only

Loop KillerFoundation

Agent Loop Killer

Repeated reads, ignored packs and loop recovery actions are surfaced.

Surface: CLI waste, dashboard waste table, MCP status, monitors
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Adoption DetectorFoundation

Agent Adoption Detector

Configured agents are checked against recent MCP usage.

Surface: Setup success, dashboard alerts, IDE sidebar, pilot report
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Deep SearchFoundation

Deep Search

Budgeted multi-step research returns citations and a stop condition.

Surface: CLI deep-search, MCP context, saved queries, dashboard evidence
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Sourcegraph parityFoundation

Sourcegraph Parity Layer

Parity language is explicit while Sourcegraph-class claims stay gated.

Surface: Compare Sourcegraph, pricing, pilot report, benchmarks
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Team Shared IndexFoundation

Team Shared Index

One commit-addressed team index with freshness and local fallback.

Surface: Team index status, dashboard, CI, MCP status
Buyer-safe status: Foundation · Foundation
Runtime: preview only

PR Context PackFoundation

PR Context Pack

Changed files, blast radius, tests, owners and risk gate are packaged.

Surface: CI artifact, dashboard PR packs, GitHub/GitLab comment
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Governed ContextFoundation

Governed Context

RBAC, redaction, denied paths and audit exports stay visible.

Surface: Governance audit, Enterprise policy, monitors, pilot report
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Pilot ReportFoundation

Pilot Report

Buyer-ready report with baseline, examples, risks and rollout tier.

Surface: CLI pilot, PDF export, dashboard, compare pages, pricing
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Batch AutopilotFoundation

Batch Autopilot

Dry-run migration plan with rollout gate before PR creation.

Surface: CLI batch-autopilot, dashboard batch runs, owners, PR metadata
Buyer-safe status: Foundation · Foundation
Runtime: preview only

InsightsFoundation

Insights & Monitoring

Saved query snapshots become trends instead of one-off searches.

Surface: Dashboard insights, saved queries, pilot report
Buyer-safe status: Foundation · Foundation
Runtime: preview only

MonitoringFoundation

Insights & Monitoring

Pattern alerts and threshold checks are explicit product surfaces.

Surface: Monitors, CI output, webhooks, governance alerts
Buyer-safe status: Foundation · Foundation
Runtime: preview only

OwnershipFoundation

Ownership & Blast Radius

Likely owners and affected tests are attached to risky changes.

Surface: PR Pack, Batch Autopilot, dashboard, IDE current diff
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Feature DiscoveryFoundation

VS Code, CLI and MCP Surfaces

No workflow ships as a hidden command or undocumented MCP action.

Surface: Feature registry, setup success, dashboard, docs, pricing
Buyer-safe status: Foundation · Foundation
Runtime: preview only

VSCodeFoundation

VS Code, CLI and MCP Surfaces

IDE actions mirror the same registry used by CLI, MCP and web.

Surface: VS Code sidebar and command palette
Buyer-safe status: Foundation · Foundation
Runtime: preview only

CLIFoundation

VS Code, CLI and MCP Surfaces

Commands expose the same feature names, statuses and JSON contracts.

Surface: aindex features, status, context, pack and workflow commands
Buyer-safe status: Foundation · Foundation
Runtime: preview only

MCPFoundation

VS Code, CLI and MCP Surfaces

Five tools route advanced actions without schema bloat.

Surface: context, search, navigate, status and remember
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Advanced Code NavigationFoundation

Advanced Code Navigation

architecture, dead-code, smells, audit, duplicates, implementations, type-hierarchy, map and rules are one router.

Surface: MCP navigate, CLI, docs, dashboard, architecture overview
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Cross-Session MemoryFoundation

Cross-Session Memory

Observations and run outcomes persist and are recalled across sessions, stored locally.

Surface: MCP remember, CLI, docs, dashboard, agent sessions
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Batch Search ToolsFoundation

Batch Search Tools

search action=batch groups related queries under one budget to cut round-trips.

Surface: MCP search, CLI, docs, dashboard, saved queries
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Self-Hosted & Air-GappedFoundation

Self-Hosted & Air-Gapped

Local SQLite index, no-network mode and metadata-only exports prove zero egress.

Surface: Security, Enterprise policy, CLI doctor, docs, dashboard
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Code Graph ExportFoundation

Code Graph Export

SCIP/LSIF interop and native full-fidelity .aig export/import keep the graph portable.

Surface: CLI scip, CLI graph, docs, dashboard, interop
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Auto-WikiFoundation

Auto-Wiki

A deterministic, metadata-only code wiki is rendered from the live graph with signatures and flows but no raw source.

Surface: CLI wiki, MCP navigate, docs, dashboard, architecture overview
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Change CouplingFoundation

Change Coupling

Git co-change pairs surface coupled neighbors a static dependency graph misses.

Surface: CLI context, MCP context, docs, dashboard, PR Pack
Buyer-safe status: Foundation · Foundation
Runtime: preview only

One-Call Context PipelineFoundation

One-Call Context Pipeline

One context call returns capsule, impact, memory recall and change-coupling together.

Surface: CLI context, MCP context, docs, dashboard, agent sessions
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Enterprise Access ControlFoundation

Enterprise Access Control

RBAC, SSO and SCIM are Enterprise entitlements enforced through governance policy.

Surface: Enterprise policy, governance audit, security, pricing, docs
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Codebase AtlasFoundation

Codebase Atlas

A deterministic, metadata-only system model, drift report and ranked risk board for any AI-built repo.

Surface: CLI understand, MCP status, Studio Atlas home, dogfood page, docs
Buyer-safe status: Foundation · Foundation
Runtime: preview only

Buyer surfaces

Billing, security, benchmarks and pricing have explicit guardrails.

These surfaces support the feature story without turning foundations into shipped enterprise claims.

Feature registryLive

Every master-plan workflow is named, linked, tiered and tied to runtime feature proof.

The registry is generated from the same source used by pricing, dashboard, setup and MCP status.

Open surface

ROI DashboardFoundation

Autopilot runs, PR packs, team index freshness, adoption, waste, insights, monitors and governance are visible as one command center.

Demo preview and observed data stay clearly separated, with metadata-only runtime evidence.

Open surface

PricingLive

Plan tiers map to named workflows with runtime observed/available kept separate.

No plan page should imply Sourcegraph-class parity for foundation workflows.

Open surface

BillingFoundation

Checkout and portal paths are visible, with readiness gates and support fallback.

Billing is presented as guarded until live-sales readiness confirms checkout.

Open surface

SecurityFoundation

Local-first source posture, redaction, audit and Governed Context are connected.

Security copy stays metadata-only and avoids claiming hosted source indexing.

Open surface

BenchmarksLive

Public benchmark data is tied back to cache-aware context and pilot proof.

Benchmark pages distinguish measured local runs from positioning claims.

Open surface

Compare SourcegraphFoundation

Search, graph, Deep Search, Batch, Insights, Monitoring, Ownership, governance and ROI are mapped to registry-backed workflows.

The page names parity expectations while keeping Sourcegraph-class claims gated by availability and runtime evidence.

Open surface

Compare Cursor/CodyFoundation

AiIndexer is presented as the neutral MCP context layer under Cursor, Cody and other assistants.

The comparison avoids replacing IDE assistants; it focuses on shared packs, adoption checks, governance and ROI proof.

Open surface

Pilot reportFoundation

Autopilot, packs, adoption, governed context, team index, Sourcegraph parity and pricing recommendations become one buyer artifact.

Observed pilot inputs stay metadata-only, with demo preview clearly separated from real report data.

Open surface

Runtime feature proof

Feature discovery is backed by metadata-only runtime evidence.

Public pages default to preview data. When a local SQLite, JSON or cloud summary is explicitly allowed, the same registry shows which workflows have been observed without exposing raw source.

0/26observed workflowsDemo preview, not runtime observed

0evidence item(s)no raw source included

26registered workflowsFeature Registry feeds web, CLI, MCP, dashboard, setup and VSCode.

4status fieldsEnabled, available, observed and buyer grade stay separate on public pages.

Non-negotiable product axes

Every release must make adoption, control, proof or parity stronger.

The product promise is not another search UI. It is a local/self-hosted context optimizer that makes agent work cheaper, faster, governed and provable.

5 minAdoptionSetup must end with Autopilot, PR Pack, Adoption Check, Pilot Report and ROI Dashboard.

local-firstControlNo raw source goes to cloud by default; self-hosted and air-gapped paths stay visible.

before/afterProofEvery workflow should tie back to tokens avoided, time saved, loops killed or risk reduced.

agent-firstParityCover search, graph, Deep Search, Batch, Insights, Monitoring, Ownership and audit.

No hidden features

Feature discovery is a product system, not a page.

The same registry has to surface in setup, CLI, MCP status, dashboard, docs, pricing, release notes and IDE actions so users cannot miss the value they already installed.

Setup success

Run Autopilot, Generate PR Pack, Check Adoption, Run Pilot Report, Open ROI Dashboard

The first successful install immediately points users to money-saving workflows.

Feature registry

Name, punchline, problem, command, MCP action, plan, maturity, proof and outcomes

Marketing, docs, pricing, setup, dashboard and release notes share the same product truth.

CLI

autopilot, pack, cache, deep-search, pr-pack, team-index, pilot, adoption, waste, governance, batch, insights, monitors, ownership

Users can discover and run workflows without reading MCP schemas or source code.

MCP

context, search, navigate, status and remember route every advanced action internally

The surface stays at five tools while still exposing enterprise workflows.

Dashboard

ROI cards, run timeline, PR packs, team index, adoption alerts, waste, insights, monitors, batch runs, governance audit

The buyer sees savings and governance evidence instead of a generic search console.

IDE

Autopilot, Pack, Cache, Deep Search, PR Pack, Loop Killer, Adoption, Team Index, ROI, Governance, Pilot, Insights, Monitoring, Batch, Ownership, Blast Radius

Agents and developers see the same actions where coding work happens.

Setup success screen

After install, the product should push users into value immediately.

These are the first five actions that make the platform visible before users forget the MCP exists.

Setup action

Run Autopilot

Shows naive tokens, optimal pack, risks, tests and do-not-read paths.

aindex autopilot "fix billing login bug" --json

MCP: context action=autopilot task="fix billing login bug"

Setup action

Generate PR Pack

Turns review into files touched, blast radius, owners, tests, risks and publish-safe comment metadata.

aindex pr-pack --pr 42 --repo owner/name --provider github --publish-comment --dry-run --json

MCP: context action=pr-pack pr=42 repo=owner/name

Setup action

Check Adoption

Confirms each agent is configured and actually calling MCP.

aindex adoption --repair --json

MCP: status detail=adoption

Setup action

Run Pilot Report

Creates JSON/PDF management proof with provenance, no raw source, savings, adoption, risk and recommendations.

aindex pilot --repos web api billing --pdf --json --output aindex-pilot-report.pdf --json-output pilot-report.json

MCP: status detail=pilotPreview: AINDEX_PILOT_REPORT_PATH=./pilot-report.json AINDEX_PILOT_REPORT_PUBLIC_OBSERVED=1 npm --prefix web run dev

Setup action

Open ROI Dashboard

Displays observed savings, waste findings, team index state and governance audit.

aindex roi --json

MCP: status detail=roi

MCP surface contract

Keep exactly five MCP tools, but make every advanced workflow discoverable.

The web presentation mirrors the product contract: no schema bloat, no hidden action names, structured output for agents and readable fallback text for humans.

Tool	Actions	Product job
context	autopilot \| pack \| cache \| deep-search \| pr-pack	Budgeted context, task packs, cache ordering, research and PR review artifacts.
search	auto \| symbols \| patterns \| regex \| exact \| saved \| cross-repo \| batch	Search remains the substrate, but results feed packs, batch dry-runs and insights.
navigate	references \| callers \| callees \| definition \| blast-radius \| tests \| ownership \| audit	Graph navigation powers risk, test prediction, review routing and governance checks.
status	features \| adoption \| waste \| roi \| governance \| insights \| monitors \| team-index	Discovery and proof live in status so agents can self-diagnose and report value.
remember	save \| search \| history \| session \| outcome	Runs, decisions and outcomes become measurable local memory instead of chat residue.

contextActionsautopilot | pack | cache | deep-search | pr-packProduct jobBudgeted context, task packs, cache ordering, research and PR review artifacts.

rememberActionssave | search | history | session | outcomeProduct jobRuns, decisions and outcomes become measurable local memory instead of chat residue.

Plans map to product workflows

Every tier unlocks a visible agent-cost workflow.

Pricing should be easy to understand: local context first, then Autopilot, then team proof, then enterprise governance.

Free

Local context, search, navigate and status
Feature registry via CLI, MCP and setup success
1 repo
Proof minimum
VS Code, CLI and MCP Surfaces
Code Graph Export

Advanced

Unlimited local repos
Agent cost workflows for individual operators
Agent Cost Autopilot
Context Packs
Cache-Aware Context
Agent Loop Killer
Agent Adoption Detector
Deep Search
VS Code, CLI and MCP Surfaces
Advanced Code Navigation
Cross-Session Memory
Batch Search Tools
Code Graph Export
Auto-Wiki
Change Coupling
One-Call Context Pipeline
Codebase Atlas

Pro

Multi-repo context
Review, ROI, ownership, monitoring and Sourcegraph-parity workflows
Agent Cost Autopilot
Context Packs
Cache-Aware Context
Proof / ROI Dashboard
Agent Loop Killer
Agent Adoption Detector
Team Shared Index
PR Context Pack
Pilot Report
Deep Search
Batch Autopilot
Insights & Monitoring
Ownership & Blast Radius
Sourcegraph Parity Layer
VS Code, CLI and MCP Surfaces
Advanced Code Navigation
Cross-Session Memory
Batch Search Tools
Code Graph Export
Auto-Wiki
Change Coupling
One-Call Context Pipeline
Codebase Atlas

Enterprise

Self-host/no-cloud source by default
Audit exports and policy firewall
SSO-ready and air-gapped mode
Enterprise security, benchmarks and procurement proof
Agent Cost Autopilot
Context Packs
Cache-Aware Context
Proof / ROI Dashboard
Agent Loop Killer
Agent Adoption Detector
Team Shared Index
PR Context Pack
Governed Context
Pilot Report
Deep Search
Batch Autopilot
Insights & Monitoring
Ownership & Blast Radius
Sourcegraph Parity Layer
VS Code, CLI and MCP Surfaces
Advanced Code Navigation
Cross-Session Memory
Batch Search Tools
Self-Hosted & Air-Gapped
Code Graph Export
Auto-Wiki
Change Coupling
One-Call Context Pipeline
Enterprise Access Control
Codebase Atlas

Free availability

VS Code, CLI and MCP SurfacesFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Code Graph ExportFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Advanced availability

Agent Cost AutopilotBetapreview onlyPilot-grade · Enabled yes · Available yes · Observed no

Context PacksBetapreview onlyPilot-grade · Enabled yes · Available yes · Observed no

Cache-Aware ContextFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Agent Loop KillerFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Agent Adoption DetectorFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Deep SearchFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

VS Code, CLI and MCP SurfacesFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Advanced Code NavigationFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Cross-Session MemoryFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Batch Search ToolsFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Code Graph ExportFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Auto-WikiFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Change CouplingFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

One-Call Context PipelineFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Codebase AtlasFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Pro availability

Agent Cost AutopilotBetapreview onlyPilot-grade · Enabled yes · Available yes · Observed no

Context PacksBetapreview onlyPilot-grade · Enabled yes · Available yes · Observed no

Cache-Aware ContextFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Proof / ROI DashboardBetapreview onlyPilot-grade · Enabled yes · Available yes · Observed no

Agent Loop KillerFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Agent Adoption DetectorFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Team Shared IndexFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

PR Context PackFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Pilot ReportFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Deep SearchFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Batch AutopilotFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Insights & MonitoringFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Ownership & Blast RadiusFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no

Sourcegraph Parity LayerFoundationpreview onlyFoundation · Enabled yes · Available yes · Observed no