Every recipe
Each one is a written walkthrough — the scenario, the steps, how to check it worked, and the mistakes worth avoiding. Personal- Remember the people you meet — Who they are, what they’re working on, what they said last time — without keeping a CRM you’ll never update.
- Keep your own promises — What you said you’d do, who you said it to, and which ones you quietly dropped.
- Think out loud, keep the thought — Say it into your phone on the walk home. It arrives as memory you can question later.
- Stop re-solving the same bug — The fix you found in March, surfaced in September — before you start debugging, not after.
- The three calls you actually need — Record what happened, retrieve what matters, reason across it. Almost every integration is these three.
- One line, keep your OpenAI SDK — Point a stock OpenAI client at Anona. Every call recalls what matters and stores what is new. No rewrite.
- Chat with your documents — Upload a file, wait for extraction, ask. Uploads land in the same space as everything else you recorded.
- Turn a meeting recording into memory — Drop in the audio. It comes back as transcribed, searchable memory nobody had to write up.
- Backfill a year of history — Queue the writes, keep serving, poll for the outcome. A blocking record waits on an LLM call; this does not.
- Know the moment ingestion finishes — Webhooks instead of polling, plus the per-space defaults that stop you resending the same options.
- Teach it your vocabulary — Your domain has words that mean something specific. Extraction can be told, once, per space.
- Browse what it knows — Page through the memories themselves — no query, no ranking. The view that answers ‘what did it actually store?’
- One space or many? — The decision you make once, early, and cannot cheaply undo. Here is how to make it right.
- Stop a runaway import — You queued fifty thousand rows from the wrong table. Here is the kill switch, and the cleanup.
- Support agent that knows each customer — One space serves every customer. Scoping keeps their histories apart, so nobody is told someone else’s story.
- Everything you know about one user — Two calls turn scoped writes into a profile, and a question you can ask about that person alone.
- Support memory the whole team shares — What one agent learns on a ticket, the next one already knows — across reps, shifts and organisations.
- Tutor that remembers the learner — Progress, sticking points and preferences that persist between sessions, months apart.
- Who your agent keeps meeting — Extraction names the people, companies and systems in every memory. Read the graph it has been building.
- What was true back then — Every memory carries two clocks. Filter on when things happened, not just when you stored them.
- Competitive intelligence that accumulates — Press releases, pricing changes and job postings become a position you can query, not a folder nobody reads.
- Financial analyst across quarters — Ask what changed between Q2 and Q4 and get an answer grounded in what was said at the time.
- Contract and policy memory — Which clause, in which agreement, agreed when — with the provenance to prove where the answer came from.
- A briefing that keeps itself current — Ask a standing question once. It rewrites its own answer as new memories arrive, and tells you when it is stale.
- Give the space a mission — Tell it what it is for, and how skeptical to be. It changes what gets kept and how it is read back.
- A shelf of standing questions — Not one self-updating briefing — a dozen, listed, edited, cleared and retired as the work moves.
- Two agents, one space — Shared knowledge with per-agent working sets, so a handoff carries everything the next agent needs.
- Memory for your coding agent — Architecture decisions, past fixes and house conventions that survive the end of the session.
- Onboarding agent for new hires — New starters ask the questions they are embarrassed to ask, and get answers from your real docs.
- Search across everything the company knows — One question, answered from the documents, decisions and conversations you have already fed it.
- Incident copilot that has read every postmortem — The last four times this broke, what fixed it, and who knew — surfaced while it is still broken.
- Account memory that outlives the rep — Stakeholders, commitments and objections stay with the account when the person handling it changes.
- Candidate memory across interviewers — Every interviewer sees what the others already covered, so the fourth conversation is not the first one again.
- Why the answer used what it used — A receipt for every retrieval: what entered the prompt, what was cut, and which of four reasons cut it.
- Correct a memory without losing the record — Supersede what turned out to be wrong, with the reason attached and the old version still readable.
- Delete a user’s memories, provably — A data-subject request answered end to end: find everything about one person, export it, remove it, show your work.
- Cut the bill without cutting recall — Cap what memory is allowed to spend of your prompt, and measure what the provider’s cache gave back.
- Prove the memory is earning its place — Run the same questions with memory on and off, and keep the number instead of the impression.
- Choose the model a space thinks with — Fourteen models, priced per operation. Pin a cheap one to a noisy space and a strong one to the space that matters.
- Take everything with you — A full export of a space — every memory and entity — as a file you hold. No SDK method; three HTTP calls.
Running any of them
What if my case isn’t here
Tell us at support@anonalabs.com. A gap in this list is a recipe we should write, and we would rather hear it from you than guess. The building blocks underneath every recipe are the same three calls —record, retrieve and
reason — so if you can describe your case in terms of
what to store and what to ask, you can usually assemble it from
Record, retrieve, reason
plus one other recipe.