llms.txt
# Falconer
> Falconer is a self-updating knowledge platform that provides humans and agents with a long-term memory system. It connects to the tools your team already uses, builds a unified knowledge base, and gives you an AI agent to search, write, and keep documentation up to date.
## Docs
- [Ask questions in Slack](https://falconer.com/docs/ask/ask-questions-in-slack.md): Ask Falcon questions directly in Slack to get instant answers from your knowledge base -- without leaving your conversation.
- [Capture decisions in Slack](https://falconer.com/docs/ask/capture-decisions-in-slack.md): Important decisions happen in Slack, then vanish. Use @Falcon remember to save any fact, decision, or context the moment it happens, right from Slack.
- [Find past conversations](https://falconer.com/docs/ask/chat-history.md): Use the Sessions page to return to earlier conversations with the Falcon agent, and pin, rename, share, or delete them.
- [Falconer vs AI chatbots](https://falconer.com/docs/ask/falconer-vs-ai-chatbots.md): Falconer and general-purpose AI assistants like Claude or ChatGPT are complementary tools. Here's how to think about when to use each.
- [Find answers with Falconer](https://falconer.com/docs/ask/find-answers-with-falconer.md): Use Falconer to instantly find answers across your codebase, docs, and tasks.
- [Personalize the agent](https://falconer.com/docs/ask/personalize-the-agent.md): Tailor every Falconer answer to your role, team, and preferences with Agent Personalization.
- [Use voice mode](https://falconer.com/docs/ask/use-voice-mode.md): Use voice mode to speak your prompts instead of typing them. Try it when you want to draft docs hands-free or describe something faster than you can type it.
- [Generate docs automatically](https://falconer.com/docs/get-started/generate-docs-automatically.md): Falconer Generate creates a complete set of documentation from your codebase -- so you're not starting from a blank page.
- [How Falconer works](https://falconer.com/docs/get-started/how-falconer-works.md): Falconer is a knowledge platform for engineering teams. It connects to the tools your team already uses, builds a unified knowledge base from them, and gives you an AI agent -- Falcon -- to search, write, and keep documentation up to date.
- [Asana](https://falconer.com/docs/integrations/asana.md): Sync projects and tasks so answers reflect the work your team is tracking.
- [Bitbucket](https://falconer.com/docs/integrations/bitbucket.md): Connect Bitbucket repositories to ask about your codebase.
- [Confluence](https://falconer.com/docs/integrations/confluence.md): Sync documentation from your Confluence spaces.
- [GitHub](https://falconer.com/docs/integrations/github.md): Connect repositories to ask about your codebase.
- [Gmail](https://falconer.com/docs/integrations/gmail.md): Connect Gmail to search your inbox live with Falconer.
- [Google Drive](https://falconer.com/docs/integrations/google-drive.md): Connect your personal Google Drive files.
- [Google Workspace](https://falconer.com/docs/integrations/google-workspace.md): Sync documents across your Google Workspace.
- [Granola](https://falconer.com/docs/integrations/granola.md): Sync meeting notes and transcripts.
- [Jira](https://falconer.com/docs/integrations/jira.md): Sync issues, projects, releases, boards, and sprints from Jira.
- [Linear](https://falconer.com/docs/integrations/linear.md): Sync issues and projects for context-aware answers.
- [Notion](https://falconer.com/docs/integrations/notion.md): Import pages and databases from your workspace.
- [Slab](https://falconer.com/docs/integrations/slab.md): Sync posts from your Slab knowledge base.
- [Slack](https://falconer.com/docs/integrations/slack.md): Ask questions and manage docs directly from Slack.
- [Zendesk](https://falconer.com/docs/integrations/zendesk.md): Import help center and support articles.
- [Falconer CLI](https://falconer.com/docs/mcp-and-cli/cli.md): Install the Falconer CLI for shell scripts and direct document operations.
- [Connect MCP](https://falconer.com/docs/mcp-and-cli/connect.md): Connect Falconer MCP to Claude.ai, Claude Code, Codex CLI, or Cursor.
- [Use organization bots with MCP](https://falconer.com/docs/mcp-and-cli/organization-bots.md): Set up an organization-level Falconer bot for local agents, sandboxes, and MCP clients.
- [Quickstart with MCP](https://falconer.com/docs/mcp-and-cli/quickstart.md): Connect Falconer MCP to your AI client, sign in with OAuth, and verify that your client can reach your Falconer documents.
- [MCP tools reference](https://falconer.com/docs/mcp-and-cli/tools-reference.md): Review the Falconer MCP tools for documents, comments, navigation, permissions, and media.
- [Vercel Connect](https://falconer.com/docs/mcp-and-cli/vercel-connect.md): Give apps and agents running on Vercel user-scoped access to Falconer through MCP.
- [Organize docs](https://falconer.com/docs/organize/organize-docs.md): Falconer Organize analyzes your Company documents and proposes a reorganized structure with new folders, categories, and architecture.
- [Spaces](https://falconer.com/docs/organize/spaces.md): Give each team or project its own area of the organization, with its own documents, members, and access.
- [Buy credits and manage auto reload](https://falconer.com/docs/plans-and-pricing/buy-credits-and-auto-reload.md): Add credits to your organization and manage automatic purchases when the shared balance runs low.
- [How credits work](https://falconer.com/docs/plans-and-pricing/how-credits-work.md): Understand shared credits, monthly grants, charged work and credit expiry on Go and Pro.
- [Enterprise Knowledge Health usage-based pricing](https://falconer.com/docs/plans-and-pricing/knowledge-health-usage-pricing.md): How Enterprise Knowledge Health subscription fees, prepaid credits, Scan metering, top-ups, and rollover work.
- [Plans and billing](https://falconer.com/docs/plans-and-pricing/plans-and-billing.md): Manage your Falconer plan, purchased seats, subscription and invoices.
- [Track usage and set spending limits](https://falconer.com/docs/plans-and-pricing/usage-and-spending-limits.md): Check your personal credit usage, review organization spending and set a monthly limit for each member.
- [Quickstart](https://falconer.com/docs/quickstart.md): Connect your first source to Falconer and ask questions or write a doc about your codebase.
- [Allowlist a domain](https://falconer.com/docs/set-up/allowlist-a-domain.md): Use the domain allowlist to allow teammates in your organization to log in with SSO.
- [Connect sources](https://falconer.com/docs/set-up/connect-sources.md): Connect your tools to Falconer to enable code-aware search, AI-powered documentation.
- [Invite teammates and manage permissions](https://falconer.com/docs/set-up/invite-teammates-and-manage-permissions.md): Get your team into Falconer and control what they can see and edit.
- [Use your own model API key](https://falconer.com/docs/set-up/use-your-own-model-api-key.md): Connect an organization provider key and pay the provider directly for model usage.
- [Images and other files](https://falconer.com/docs/two-way-sync/images-and-files.md): How images, assets, and other non-Markdown files sync with the repository.
- [Manage or disconnect sync](https://falconer.com/docs/two-way-sync/manage-sync.md): Change sync settings, retry a failed sync, or disconnect a space from its repository.
- [Move, rename, and delete](https://falconer.com/docs/two-way-sync/move-rename-delete.md): How moving, renaming, and deleting documents carries over to the repository.
- [How two-way sync works](https://falconer.com/docs/two-way-sync/overview.md): Keep a Falconer space and a GitHub repository in sync, in both directions.
- [Get changes from GitHub](https://falconer.com/docs/two-way-sync/pull-changes-from-github.md): How commits on GitHub reach Falconer, and how to resolve conflicts.
- [Push changes to GitHub](https://falconer.com/docs/two-way-sync/push-changes.md): Send your Falconer edits to GitHub as a commit or a pull request.
- [Set up two-way sync](https://falconer.com/docs/two-way-sync/set-up-two-way-sync.md): Connect a space to a GitHub repository and import its docs.
- [Supported Markdown and limits](https://falconer.com/docs/two-way-sync/supported-markdown.md): Which Markdown and MDX features sync with Falconer, and what to know before you sync.
- [Understand sync status](https://falconer.com/docs/two-way-sync/sync-status.md): Read sync status labels and use the GitHub sync drawer to see what needs attention.
- [Automatically update documents](https://falconer.com/docs/update/auto-update-docs.md): Turn on auto-update for any document and Falconer will keep it current, automatically. When a pull request merges, Falconer reads the diff, finds which docs are affected, and proposes changes for your review.
- [Edit a doc with inline AI](https://falconer.com/docs/update/edit-a-doc-with-inline-ai.md): Use inline AI to make targeted edits to specific sections instead of regenerating an entire page.
- [Find and fix outdated docs](https://falconer.com/docs/update/find-and-fix-outdated-docs.md): Ask Falcon to audit your documentation for staleness -- from inside a doc or from the homepage -- and get a prioritized list of what needs updating.
- [Keep docs in sync with PRs](https://falconer.com/docs/update/keep-docs-in-sync-with-prs.md): Get notified when pull requests impact your docs. Falconer automatically detects when a merged pull request impacts your existing documentation and proposes targeted updates.
- [Run Knowledge Health](https://falconer.com/docs/update/run-knowledge-health.md): Scan connected sources for knowledge issues, review findings, and manage credit-funded runs.
- [Update docs from Slack](https://falconer.com/docs/update/update-docs-from-slack.md): Update your Falconer docs directly from Slack conversations.
- [Create Linear issues from Falconer](https://falconer.com/docs/use-cases/automate-workflows/create-linear-issues-from-falconer.md): Create Linear issues from Slack conversation or Falconer docs.
- [Sync Granola meeting notes](https://falconer.com/docs/use-cases/automate-workflows/sync-granola-meeting-notes.md): Connecting Granola syncs your meeting notes into Falconer, making them searchable alongside your docs, code, and conversations.
- [Talk to the Falconer agent like a teammate](https://falconer.com/docs/use-cases/automate-workflows/talk-to-the-falconer-agent-like-a-teammate.md): Get answers and capture your knowledge in plain conversation -- no prompts required.
- [Update docs when code changes](https://falconer.com/docs/use-cases/automate-workflows/update-docs-when-code-changes.md): Automatically keep documentation in sync with your codebase as your team ships.
- [Create an onboarding guide](https://falconer.com/docs/use-cases/generate-documents/create-an-onboarding-guide.md): Create role-specific onboarding guides for new hires using existing context.
- [Create architecture overviews](https://falconer.com/docs/use-cases/generate-documents/create-architecture-overviews.md): Ask Falconer to explain how any part of your codebase works -- from high-level system architecture down to how a specific feature is implemented.
- [Generate a weekly team report](https://falconer.com/docs/use-cases/generate-documents/generate-a-weekly-team-report.md): Summarize what your team shipped, what's in progress, and what's blocked in minutes.
- [Generate an API reference from code](https://falconer.com/docs/use-cases/generate-documents/generate-an-api-reference-from-code.md): Turn your codebase into a structured API reference. Falconer reads your connected repositories and generates documentation for your endpoints, functions, parameters, and return types.
- [Write a changelog](https://falconer.com/docs/use-cases/generate-documents/write-a-changelog.md): Generate a changelog using context from your connected sources.
- [Write a runbook](https://falconer.com/docs/use-cases/generate-documents/write-a-runbook.md): Turn your codebase, Slack threads, and notes into step-by-step runbooks ready for the next incident or deployment.
- [Choose inherited or custom permissions](https://falconer.com/docs/use-cases/manage-permissions/choose-inherited-custom-permissions.md): Decide whether a doc or folder should follow its parent permissions or keep its own access settings.
- [Manage folder access](https://falconer.com/docs/use-cases/manage-permissions/manage-folder-access.md): Use folder permissions to manage access for groups of related docs.
- [Plan doc access](https://falconer.com/docs/use-cases/manage-permissions/plan-doc-access.md): Plan who should be able to view, comment on, edit, and share docs before you update permissions.
- [Share a doc](https://falconer.com/docs/use-cases/manage-permissions/share-a-doc.md): Give the right people access to one doc, manage authors, and control link access.
- [Troubleshooting access](https://falconer.com/docs/use-cases/manage-permissions/troubleshooting-access.md): Answers to the most common surprises about who can see, find, and edit your docs.
- [Create skill docs](https://falconer.com/docs/use-cases/skill-docs/create-skill-docs.md): Turn Falconer documents into reusable skill docs that give Falcon instructions for repeatable workflows.
- [Use skill docs](https://falconer.com/docs/use-cases/skill-docs/use-skill-docs.md): Reference skill docs in Falconer chat to give Falcon reusable instructions for repeatable work.
- [Comment on a doc](https://falconer.com/docs/write/comment-on-a-doc.md): Leave comments on any part of a doc, discuss them in threads, and share a link that opens a specific comment.
- [Write a doc from Slack](https://falconer.com/docs/write/write-a-doc-from-slack.md): Turn any Slack conversation into a structured Falconer document.
- [Write a doc](https://falconer.com/docs/write/write-a-doc.md): Write with AI, with your sources as context, or start from a blank slate.
## Notes
- [Agent loops are fine, retrieval is what you're paying for](https://falconer.com/notes/agent-loops-retrieval-cost.md): Inefficient retrieval is burning your token budget. When the first search comes back incomplete, context grows and the bill follows.
- [Agent Personalization: an agent that knows you](https://falconer.com/notes/agent-personalization.md): Falconer now tailors every response to who you are. Agent Personalization builds a lightweight, transparent profile of your role, team, and preferences — fully editable, with every attribute traced back to its source.
- [Why everything breaks at 150 people](https://falconer.com/notes/cerebras-knowledge-base.md): Cerebras's post on building their internal knowledge base hit 2.5M views. From someone who led knowledge management at Stripe and Uber: why knowledge bases break around 150 people, what a great one looks like, and how to roll one out.
- [Your context is more than training data](https://falconer.com/notes/context-more-than-training-data.md): Everyone has access to the same frontier models. Your competitive advantage is institutional context — the decisions, tradeoffs, and battle scars inside your four walls. Here's why curating that context is now existential.
- [Docs-as-code as simple as Google Docs](https://falconer.com/notes/docs-stuck-in-repos.md): Customer guides, onboarding flows, API references: they live in the codebase, where the people who write them can't easily edit. So they keep a working copy somewhere else and maintain two versions of the same thing, forever.
- [Falconer agent now speaks git](https://falconer.com/notes/falconer-agent-now-speaks-git.md): The Falconer agent can now answer questions about your code's history: who wrote what, when, and why. It calls git directly against your connected repos to do code archaeology, release diffs, regression hunts, and ownership lookups, all in a chat.
- [Falconer Generate: from repo to doc set in minutes](https://falconer.com/notes/falconer-generate-from-repo-to-doc-set-in-minutes.md): Falconer Generate turns a connected GitHub repo into a structured documentation set, helping teams get documentation started faster.
- [Spaces: focused work, connected knowledge](https://falconer.com/notes/falconer-spaces.md): One knowledge tree gets noisy as a company grows, but separate workspaces create silos. Spaces give each team a focused view while preserving the context, permissions, and decisions that connect everything, with no migration required.
- [Falconer Update: Full self-driving docs](https://falconer.com/notes/falconer-update-self-driving-docs.md): Falconer Update keeps your documentation in sync with your codebase automatically. Toggle it on for any document and choose Review mode for human-in-the-loop edits, or Full Self-Driving mode to let Falconer handle it entirely.
- [How to generate a changelog in 10 seconds](https://falconer.com/notes/generate-changelog.md): Changelogs used to take hours each week to assemble across GitHub, Linear, Slack, and meeting notes. Falconer turns the same week of context into a changelog in seconds — already cited, audience-aware, and ready to send.
- [Ditching the agent sandbox for AWS S3 Files](https://falconer.com/notes/how-falconer-powers-agents-with-aws-s3-files.md): How we gave the Falconer agent git access (log, blame, diff between arbitrary refs) by mounting a shared NFS filesystem backed by S3 Files across our ingest and UI services. A walkthrough of the storage choice, the Pulumi quirks, and how we made the repo sync robust and reliable.
- [How others build agent memory, and what I took from each](https://falconer.com/notes/how-others-build-agent-memory.md): ChatGPT, Claude Code, and Letta have each built production memory systems for AI agents. Looking at the differences shaped how I built agent signals for Falconer.
- [Knowledge as code](https://falconer.com/notes/knowledge-as-code.md): Only one breakout AI use case is making a significant impact on knowledge work: coding, because code is versioned, tested, and machine readable. Treating company knowledge the same way, centrally stored, versioned, and observable, is how the rest of the organization gets that same leverage.
- [Knowledge Health: observability for your knowledge base](https://falconer.com/notes/knowledge-health.md): Every company runs on written knowledge, and almost none of them know how healthy theirs is. Knowledge Health puts a single, live score on it and shows you exactly what's dragging it down: contradictions, stale docs, coverage gaps, and redundancies.
- [The source of truth for high-speed teams](https://falconer.com/notes/launch.md): Our mission is to capture all of your important context, keep it up to date, and make it easy for you to deploy it wherever you want: your teammates, your customers, your coding agents.
- [LLM-as-a-Courtroom](https://falconer.com/notes/llm-as-a-courtroom.md): How we built a multi-agent courtroom simulation to decide when code changes require documentation updates—and why the legal system is humanity's best framework for binary decisions under uncertainty.
- [Rethinking data ingestion as a DAG](https://falconer.com/notes/rethinking-data-ingestion-dag.md): How we reduced data ingestion time from hours to minutes by reimagining our pipeline as a directed acyclic graph. This post covers the architectural shift from async workflows to job queues, the migration strategy we used to preserve behavior, and the observability patterns that helped us identify and isolate bottlenecks at scale.
- [Search, rebuilt: how Falconer finds the right answer](https://falconer.com/notes/search-rebuilt.md): Company search is hard: the corpus is too large to browse and too small to learn ranking from. Here's how Falconer's search page and answer engine find the right answer.
- [Skill documents: shared team instructions for every AI tool](https://falconer.com/notes/skill-documents.md): Falconer Skill documents let teams create, share,
