https://falconer.com/notes Essays, announcements, and research from the team behind Falconer. en-us Thu, 29 Oct 2026 12:00:00 GMT https://falconer.com/notes/two-copies-of-truth https://falconer.com/notes/two-copies-of-truth Thu, 29 Oct 2026 12:00:00 GMT Apoorva Shete Most teams keep docs in two places, Markdown in GitHub and a polished copy in an editor, and both drift. Two-way sync keeps them one shared document. https://falconer.com/notes/on-prem-falconer https://falconer.com/notes/on-prem-falconer Tue, 27 Oct 2026 12:00:00 GMT Lilu Xu Put your company's knowledge to work with an AI-native knowledge base that runs in your own cloud account, with the sources and model providers you approve. https://falconer.com/notes/root-out-false-information https://falconer.com/notes/root-out-false-information Fri, 23 Oct 2026 12:00:00 GMT Aryaman Agrawal Wrong information spreads through a company like a poisonous seed. Knowledge Health finds it across your docs and code before your team and your agents build on it. https://falconer.com/notes/documentation-new-purpose https://falconer.com/notes/documentation-new-purpose Wed, 21 Oct 2026 12:00:00 GMT Giorgio Garofalo Agents now handle the step-by-step tasks docs used to explain, so documentation has to serve people and agents at once. Public Docs, in beta now, publishes customer-facing documentation from the same knowledge base your team already uses internally. https://falconer.com/notes/falconer-knowledge-platform https://falconer.com/notes/falconer-knowledge-platform Wed, 21 Oct 2026 12:00:00 GMT Dave Nunez Falconer gives you and your customers complete, specialized intelligence: an internal knowledge base and external documentation in one beautiful package. https://falconer.com/notes/usage-based-pricing https://falconer.com/notes/usage-based-pricing Thu, 15 Oct 2026 12:00:00 GMT One shared credit balance for AI features, Knowledge Health, and paid public-docs add-ons gives teams more flexibility and a clearer view of spending. https://falconer.com/notes/knowledge-as-code https://falconer.com/notes/knowledge-as-code Thu, 10 Sep 2026 12:00:00 GMT Dave Nunez 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. https://falconer.com/notes/falconer-spaces https://falconer.com/notes/falconer-spaces Thu, 13 Aug 2026 12:00:00 GMT Quinn Dupies 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. https://falconer.com/notes/cerebras-knowledge-base https://falconer.com/notes/cerebras-knowledge-base Fri, 24 Jul 2026 12:00:00 GMT Dave Nunez 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. https://falconer.com/notes/docs-stuck-in-repos https://falconer.com/notes/docs-stuck-in-repos Thu, 25 Jun 2026 12:00:00 GMT Apoorva Shete 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. https://falconer.com/notes/search-rebuilt https://falconer.com/notes/search-rebuilt Tue, 23 Jun 2026 12:00:00 GMT Aryaman Agrawal 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. https://falconer.com/notes/agent-loops-retrieval-cost https://falconer.com/notes/agent-loops-retrieval-cost Thu, 11 Jun 2026 12:00:00 GMT Giorgio Garofalo Inefficient retrieval is burning your token budget. When the first search comes back incomplete, context grows and the bill follows. https://falconer.com/notes/skill-documents https://falconer.com/notes/skill-documents Wed, 03 Jun 2026 12:00:00 GMT Lilu Xu Falconer Skill documents let teams create, share, manage, and reuse AI instructions across Falconer and MCP-connected tools like Claude, Cursor, and Codex. https://falconer.com/notes/stop-freeloading-open-source https://falconer.com/notes/stop-freeloading-open-source Wed, 03 Jun 2026 12:00:00 GMT Giorgio Garofalo Most teams quietly work around the rough edges of the open source libraries they depend on. We decided to fix them at the source instead, contributing patches upstream to Tiptap, the framework behind Falconer's editor. https://falconer.com/notes/generate-changelog https://falconer.com/notes/generate-changelog Fri, 29 May 2026 12:00:00 GMT Quinn Dupies 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. https://falconer.com/notes/falconer-agent-now-speaks-git https://falconer.com/notes/falconer-agent-now-speaks-git Wed, 27 May 2026 12:00:00 GMT Matt Zhao 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. https://falconer.com/notes/how-falconer-powers-agents-with-aws-s3-files https://falconer.com/notes/how-falconer-powers-agents-with-aws-s3-files Wed, 27 May 2026 12:00:00 GMT Matt Zhao 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. https://falconer.com/notes/how-others-build-agent-memory https://falconer.com/notes/how-others-build-agent-memory Thu, 21 May 2026 12:00:00 GMT Apoorva Shete 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. https://falconer.com/notes/knowledge-health https://falconer.com/notes/knowledge-health Thu, 21 May 2026 12:00:00 GMT Aryaman Agrawal 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. https://falconer.com/notes/agent-personalization https://falconer.com/notes/agent-personalization Tue, 28 Apr 2026 12:00:00 GMT Apoorva Shete 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. https://falconer.com/notes/context-more-than-training-data https://falconer.com/notes/context-more-than-training-data Wed, 22 Apr 2026 12:00:00 GMT Dave Nunez 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. https://falconer.com/notes/falconer-update-self-driving-docs https://falconer.com/notes/falconer-update-self-driving-docs Thu, 09 Apr 2026 12:00:00 GMT Matt Zhao 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. https://falconer.com/notes/falconer-generate-from-repo-to-doc-set-in-minutes https://falconer.com/notes/falconer-generate-from-repo-to-doc-set-in-minutes Thu, 12 Mar 2026 12:00:00 GMT Lilu Xu Falconer Generate turns a connected GitHub repo into a structured documentation set, helping teams get documentation started faster. https://falconer.com/notes/launch https://falconer.com/notes/launch Tue, 10 Feb 2026 12:00:00 GMT Dave Nunez 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. https://falconer.com/notes/rethinking-data-ingestion-dag https://falconer.com/notes/rethinking-data-ingestion-dag Wed, 04 Feb 2026 12:00:00 GMT Apoorva Shete 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. https://falconer.com/notes/llm-as-a-courtroom https://falconer.com/notes/llm-as-a-courtroom Mon, 19 Jan 2026 12:00:00 GMT Aryaman Agrawal 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.