DeployIt blog — product knowledge for humans and AI agents
Guides on MCP servers, wiring support agents like Intercom Fin or HubSpot Breeze to your codebase, and keeping product knowledge — docs, changelogs, help centers — up to date at every deploy.
New here? Start with the MCP server for your codebase, or see how the same expert answers your team in the AI Help Center & Messenger.
Which customer questions can customer success settle from the code?
From kickoff to renewal, many of the questions a customer puts to their CS contact have an answer in the code and the git history. How to sort them, stage by stage of the account.
Read more →How do you know which of your AI agent's answers changed after a release?
Replay a fixed list of questions after every release and compare with the previous run. The most dangerous answer is the one that should have changed and did not move.
Read more →How do you test an MCP server before agents start using it?
Test an MCP server in two passes: the protocol with the Inspector, then the answers with a fixed sheet of questions that includes the ones it must refuse.
Read more →How do you change an MCP server without breaking the agents already using it?
An MCP tool has no version field. Change it safely by adding first, warning in the description, and removing last. A rename traced over four dates.
Read more →How do you evaluate an MCP server before connecting it to your product?
An MCP server is judged by what it answers the day after a release, not by its listing. A twenty-minute trial, six tests, for product teams.
Read more →Which product questions can you answer without interrupting an engineer?
Most product questions from PMs and sales have an answer in the code. One day of questions, sorted, to see which ones really need an engineer.
Read more →Your internal wiki contradicts the code: which one do you trust?
When the wiki and the code disagree, the code wins on what the product does, the wiki on why and how the team works. A precedence rule, sentence by sentence.
Read more →How do you announce an API or feature removal so nobody misses it?
A deprecation notice fails when it is read, understood, then forgotten. What it must contain, when to repeat it, and how to derive it from the code instead of writing it from memory.
Read more →Changelog, release notes, "What's new": which one do you need?
One change, three artefacts, three different texts. A worked example shows what each of a changelog, release notes and a "What's new" page keeps, drops and rewrites, and how to pick.
Read more →What should an AI agent refuse to answer about your product?
An agent should refuse whatever the code cannot prove: roadmap, unpublished prices, commitments. A sorting test of eight questions shows where the line falls.
Read more →Why does your AI agent say a feature doesn't exist when it shipped last week?
A denial of a feature that exists has one of four causes. Four questions, asked in order, tell you which one you are looking at, and what to change.
Read more →How do you write MCP tool descriptions an agent actually uses correctly?
An agent picks an MCP tool from its description and nothing else. Four rewrite passes turn a vague entry into one that gets called for the right questions and skipped for the wrong ones.
Read more →How do you keep developer portal content current between redesigns?
A developer portal ages page by page, not all at once. The way out: know which pages carry a fact from the code, and recompute those from the code instead of rereading them by hand.
Read more →How do you publish release notes in several languages without retranslating them every release?
Retranslating release notes each release makes the languages drift apart. The way out: one source of facts, translations that carry only the form, and the same set of facts in every language.
Read more →Why do your support macros go stale after every release?
A support macro is an answer written by hand on a given day: the next release makes it wrong and nobody reopens it. A post-mortem of an illustrative macro, and the routine that keeps macros current.
Read more →What happens in the first week an AI agent is connected to your product?
The first seven days of an agent connected to your product: the questions that land, the ones that miss, the ones left unanswered, and what you adjust on your side. An illustrative scenario with no usage figures.
Read more →Why does an AI agent answer differently on staging than on production?
Same agent, same question, two answers: staging and production are not the same product, and the agent answers from whichever state its source reflects. Four sources, four ages, and the question to ask before you connect one.
Read more →What security questions should you ask an MCP server vendor?
Twelve questions, in four blocks, that a security team can put to any MCP server vendor: who can call it, what it can read, what it can do, and what you can prove afterwards. For each, the answer that closes the point and the one that leaves it open.
Read more →How do you connect Cursor or Windsurf to your product knowledge?
Both editors accept a remote MCP server from one JSON entry. Here are the two entries side by side, as the docs stated them on 13 October 2026, and what an editor can ask a product expert that it cannot ask the open file.
Read more →What should you expose when you build an MCP server on your own SaaS?
The catalog of an MCP server is a product decision, not an export of your API. Three questions sort what an outside agent should be able to call.
Read more →How do you keep an engineering team's onboarding docs current?
An onboarding guide goes stale because it describes the code as it was the day it was written. Pull the facts from the code itself, and keep by hand only what no code can say.
Read more →What should an API changelog for integrators contain?
An integrator reads an API changelog to decide one thing: do I have to touch my code? Six fields answer it, and most changelogs carry two.
Read more →Why does my AI agent give wrong answers about our API after a release?
An agent plugged into your API documentation answers with the API as it was last documented. After a release, the gap is invisible to it. What to hand it instead.
Read more →Where does the data go when an AI agent asks questions about your product?
A question to a product-knowledge server travels through four places: the Git provider, the vendor's infrastructure, a language-model provider, and the platform that asked. Self-hosting your portal settles the first two at most. Here is what DeployIt's public DPA says about each, and what it leaves open.
Read more →How does an AI agent authenticate to an MCP server?
An agent authenticates to a remote MCP server with an OAuth access token, obtained through a flow the server starts by answering 401. What that token can do, and what revoking it actually cuts, depends on which of three credentials you mean.
Read more →Can you generate Notion documentation from your code without overwriting what your team writes?
Generating Notion documentation from code is the easy part; making it coexist with what your team writes by hand is the real problem. The four writing rules that decide whether the page survives.
Read more →How do you ask your codebase questions via an API?
An MCP server in front of your codebase turns a plain-language question into a sourced answer. The real shift: the caller is no longer a person, and nobody proof-reads before the answer gets used.
Read more →How do you reduce developer interruptions from support?
Support questions that escalate to developers fall into four cases. Only one is fixed by better documentation; the most common one has no answer outside a diff.
Read more →How do you build a "What's new" page generated from git?
A "What's new" page is not a changelog with better styling: its window belongs to the reader, not to the release. What you have to derive from diffs to make it work, and the triage that remains.
Read more →How do you give AI agents access to your code safely?
The safe model is not opening your repository to an agent. It is opening a place that answers questions about it. One access grant followed across five moments, and the four properties tested at each.
Read more →Why does our AI agent hallucinate product features?
An agent invents a feature because it has to answer and nothing forces it to check first. The four shapes that invention takes, and the condition missing when a connected source fails to stop it.
Read more →Context7 and DeepWiki on a private repo: what does each one cover?
Context7 indexes written documentation; DeepWiki builds a conversational wiki of public repositories. On a private repo, both move you onto a paid plan, and neither documents access to commits.
Read more →Claude project knowledge vs an MCP server: which one knows what changed?
Project knowledge is a folder of files, frozen at your last click on Sync, with no history. An MCP server is a source queried at the moment the question is asked. One week in a repository shows the difference.
Read more →How do you detect documentation drift?
You do not find a stale page by rereading it. You start from the diffs of the period and work back to the pages they invalidated. The manual audit, its blind spots, and continuous detection.
Read more →GitHub MCP server: how to set it up, and what it can actually answer
Setup in three minutes, the list of what it answers well, and the call log that shows where it breaks down: reading a diff is one call per commit, and it is not the default.
Read more →How do you keep a help center in sync with releases?
Not by writing faster: by deriving the pages from the source that changes. The back-of-the-envelope maths behind why manual updating falls behind, the four surfaces a release invalidates at once, and the loop that holds.
Read more →Can you connect HubSpot Breeze to your codebase?
Not the way you connect Intercom Fin. Breeze only talks to MCP servers HubSpot has vetted — here is the dated record of what the docs allow, and the two routes that actually work for grounding a Breeze agent in your code.
Read more →Release Awareness: Why Must an AI Agent Know What Just Changed?
An agent that missed your last release answers about a product that no longer exists. What release awareness is, how to test yours in three questions, and what to connect to get it.
Read more →Docs drift: why does every knowledge base end up outdated?
Docs drift is not carelessness, it is mechanics: a frozen text describes a product that keeps changing without it. Its four forms, and the only way out that holds.
Read more →How do you generate release notes your customers actually read?
A reformatted git log is not a release note. What makes one readable: derive the impact from real diffs, speak the customer's language, say what to do.
Read more →How Do You Write Release Notes for Multiple Audiences Without Rewriting Them Three Times?
Customer changelog, internal note, support answers: three rewrites of the same release. The way out: derive those views from one source — your git history.
Read more →MCP vs RAG: Which Approach for Codebase Knowledge?
RAG indexes a snapshot of your code; MCP lets the agent explore the repository at question time. What each approach sees, what it misses, and when to combine them.
Read more →Did the API Change This Week? Spotting Breaking Changes in Real Diffs
The integrator's weekly question: where breaking changes hide when the changelog says nothing, and how to answer from the real diffs.
Read more →How to Automate a Changelog From Your Git History
Message-based generators or a changelog derived from real diffs: the five-question test that separates the approaches, for your customers and your agents.
Read more →Why Did This Behavior Change? Answers From Your Git History
The product works, just differently than last week: the post-release mystery ticket. Trace the symptom to the diff that explains it, no interruptions.
Read more →How to Let AI Work on Client Code Without Breaching the NDA
Contractors, AI agents, and support teams need answers about a client's product under NDA, not its code. How to split the two flows.
Read more →AI Release Notes Generator: What These Tools Actually Read
What release notes generators actually read — git-cliff, release-please, AI layers — and the approach that derives notes from real diffs.
Read more →Why Does Your Support Bot Give Outdated Answers After a Release?
The classic post-release support bug: the bot answers from a frozen copy of your product. Why it happens on every deploy, and the fix that holds.
Read more →How to Connect Intercom Fin to Your Codebase
A step-by-step guide to Fin's custom MCP connector: plug in a product expert derived from your real code — without handing anyone a GitHub token.
Read more →What Changed in the Product This Week?
The most useful question you can ask about a product — and why the reliable answer comes from your repo's real diffs, asked through Claude via MCP.
Read more →Connect Claude to Your GitHub Repo — and What It Can't See
A step-by-step guide to Claude's GitHub connector, its documented limit — no commit history — and how to still answer "what changed this week?".
Read more →Why Doesn't Your AI Support Agent Know Your Product?
AI support agents answer from a frozen copy of your product, not from what you just shipped. Why that is structural — and how to ground them in your real code.
Read more →What Is an MCP Server? A Plain-Language Explanation
An MCP server is a standard socket between your data sources and AI agents. A plain definition, how it works, use cases — and the private-product gap.
Read more →Dev-Days: The Honest Unit for Developer Output
Lines of code, commits, story points, hours: all of these count gestures. The dev-day (≈ 5 hours of focused production) estimates what got produced — humans and AI agents alike.
Read more →Know What Your Developers Shipped — Without Standups
Reporting standups are expensive and still tell you neither what shipped nor what is stuck. Replace them with a Monday weekly report and a real-time dashboard, read-only.
Read more →Swarmia Alternative for Non-Technical Leaders
Swarmia speaks to VP Engineering: DORA, sprints, benchmarks. Here is the alternative for non-technical leaders who want to read what shipped — humans and AI agents — without the jargon.
Read more →DORA Metrics Dashboard vs Shipping Cadence Reports: When to Use Each
A practical comparison of DORA dashboards and shipping cadence reports, plus a field-level recipe to build a hybrid scorecard from your Git/CI data in a day.
Read more →Engineering velocity tracking without scoring: a practical system
A hands-on plan to instrument GitHub, issues, and deploys to track flow using bands, checks, and baselines—no subjective scoring, no vendor lock-in.
Read more →Engineering Velocity Improvements Without Scoring: Playbook
A practical, no-leaderboard approach to accelerate delivery by removing wait states, shrinking change size, and tightening CI/CD feedback using defaults in common dev tools.
Read more →Guide to Using a DORA Metrics Dashboard Effectively
A concrete, pro‑dev playbook for instrumenting DORA events, designing decision‑ready dashboards, and running weekly rituals that actually move delivery outcomes.
Read more →How to Improve Engineering Visibility for CTOs: A Practical Playbook
A vendor‑neutral plan for CTOs to make engineering work visible with DORA, SPACE, and SLOs—using Git/CI/incident data to drive a one‑page dashboard and an operating cadence.
Read more →How to Choose a LinearB Alternative: Engineer-First Guide
A pragmatic, tool-agnostic checklist and 30-day proof-of-value to choose a LinearB alternative developers trust, with data-quality gates and clear adoption signals.
Read more →Architecture Decision Records from Git: Always Current
ADRs go stale as soon as the code moves on. Derive them from git history so every decision record stays current, traceable and auditable — for humans and AI agents.
Read more →Engineering 1:1s Anchored in Delivery: Fewer Surprises
Anchor engineering 1:1s in pull requests, commits, and releases. Agendas, prompts, and a Monday delivery report that cut surprises and raise predictability.
Read more →Risk Detection from Commit Patterns: Actionable Signals
Learn how commit patterns reveal hotspots, migrations, and auth-sensitive edits, with read-only signals your team can act on before incidents.
Read more →Git Activity Dashboard for Non‑Tech: Clear Rhythm
Explore a git activity dashboard non technical leaders can use to see ship cadence, PRs, cycle time, and trends—no code needed. Clear, actionable views.
Read more →DORA Metrics for Small SaaS Teams: Prioritize What Matters
DORA metrics for small saas teams: focus on deploy freq, lead time, change fail rate, MTTR to cut noise and improve outcomes. Practical guardrails and steps.
Read more →Explain Engineering Velocity to Investors: Clear Proof
Explain engineering velocity to investors with auditable proof from the repo: shipped releases, effort in dev-days, and quarterly board-ready reports.
Read more →Roadmap vs Actual Delivery: Founder-Ready View
See roadmap vs actual delivery with clear metrics, variance alerts, and founder-ready visibility. Improve predictability and trust across product teams.
Read more →Sprint Review from Git History: Clear Demos Fast
Run a sprint review from git history to build clear, fast demos. Turn commits, PRs, and diffs into stakeholder-ready stories with traceable evidence.
Read more →Release Cadence Metrics for SaaS: Predictable Shipping
Learn the release cadence metrics that make SaaS shipping predictable: release frequency, batch size, and lead-time bands — reported every Monday, in dev-days.
Read more →Track Engineering Progress Weekly — No Micromanaging
How to track engineering progress without micromanaging: a read-only weekly report covering humans and AI agents, delivered every Monday.
Read more →Weekly Engineering Digest Template: Ship in 10 Minutes
Use this weekly engineering digest template to build a ship rhythm in 10 minutes — sections, examples, and how DeployIt emails it automatically every Monday.
Read more →10 minutes now. The dashboard tonight, your first report on Monday. You decide.
Free plan, no credit card. Read-only. No action required from your team.
Free plan · No CC · Read-only · Hosted in EU