VoiceDebrief iOS / crm / workflows

SGit CRM as workflows made of cells

How SGit CRM is put together, and what it sells: cells, combined into workflows, combined into plays, which together are the CRM. Written 16 November 2026 by the CRM cell (cells/crm-ios/) at the owner's request, after the ten workflows mapped for Algarve Evolution (Ten agentic cells for the death by a thousand cuts, a prototype not yet approved by Algarve Evolution). Status: six workflows are built (W1, W3, W5, W11, W12, W13) and the rest are proposed; each says which.

The idea in four layers

LayerWhat it isWhat a buyer getsIn the app
CellOne unit of work, with its own reach: a piece of code, one model call, an agent's loop, or a person's decisionA part that can be tested alone and reused in other workflowsA Swift type or a lane, with a test
WorkflowCells joined end to end, from a trigger to a record, with a policy and a person's approval before anything leavesOne job done the way a person would do it, only faster: "import the summit contacts", "draft a follow-up"A screen that runs it, and a commit at the end
PlayA named sequence of workflows the team repeats ("after a conference", "an investor round")A way of workingA plays/ record in the vault (the format has them)
The CRMThe plays, the workflows they use, and the records they leave in the user's vaultThe product on the App StoreSGit CRM

So we do not sell "a CRM" first. We sell workflows, each made of cells we have tested, and the CRM is what you have once you run several of them. A customer can start with one workflow; the AgentiCCells ladder (one agent, a few sessions, a team, a network) says how far it grows.

Kinds of cell, by altitude

The altitudes of a run (from the Swarm demo of 12 November, in six setups of an agentic system) are the kinds of cell. Each kind has a cost, a reach and a place it may run.

AltitudeCellExample in the CRMCostWhere it runs
A0Code cell: plain code, deterministic, testedthe vCard reader, the matcher, the commitnothing per runin the app
A1On-device model cell: one call to Apple's models (Vision, the Foundation Models framework)reading the text on a badge photonothing per run; nothing leaves the devicein the app
A1Cloud model cell: one call to Claude, or through OpenRouterdrafting a follow-up in our voiceper calloutside the app, behind a lane: the app holds no API key
A2, A3Agent cell: a loop with tools and a key of its ownmerging duplicates, enriching with sourcesper runa Claude session, writing proposals to an append lane
PPerson cell: a decision only a person may takeaccepting a proposal, sending a messagea person's timein the app

Cells move down the altitudes as we learn. A job is first done by an agent, because nobody knows its shape yet; once its shape is known, an agent writes it as code, and the code cell replaces the agent cell: fewer moving parts, no cost per run, nothing to reach. The card-text reader is already one: plain rules where a model might have been, tested on invented cards. Every cell keeps the same promise wherever it sits: the policy says what it can reach (the grant), what it was asked to do (the mandate), the difference (the gap) and what stops it (the barriers).

What every workflow has

As in the Algarve Evolution map: a trigger (a vault, a photo, a voice note, a date, a reply); cells that read, match and draft; a policy check; a person who approves anything that leaves or changes a record; a record of what changed and which key changed it (one signed commit per batch, in the user's CRM vault). No workflow sends a message: the CRM drafts, a person sends.

Twelve workflows for the CRM

The first use is the Web Summit 2026 follow-up, so the first workflows are the ones that turn the summit into follow-ups. Times are illustrative estimates for discussion, not measurements.

#WorkflowTriggerCellsWrites (proposals)Waits for a personTime, illustrativeLadderStatus
W1Import contacts from a vaulta vault key or QR code; a vault of vaults such as crm-sourcesA0 vault reader, format readers (vCard, CSV, JSON, team CRM layout), matcher, planner, commit; A1 Vision on badge photos; P reviewpeople, organisations, interactions, follow-upsevery proposal, one by one or all at once4 hours a list → 20 minone agent's worth, all in the appunverified: built, CI is the test, not tried on a device
W2Capture at a standa photo of a badge or card, or ten seconds of voiceA1 Vision; A1 Foundation Models (one question: who, where, what next); A0 matcher; Pa person, an interaction, a follow-upthe proposal5 min → 30 sin the appproposed
W3Who needs what todayopening the app; a dateA0 the list: due, overdue, waiting on someone, by owner; P changes a follow-upa changed follow-up, as a signed commitevery change30 min a day → glancein the appunverified: built (step 4), CI is the test, not tried on a device
W4Draft a follow-up in our voicea follow-up that is dueA1 cloud model behind a lane, or A1 on-device for a short note; A0 template; P edits and sends from the Mail or Messages sheeta draft; then an interaction once sentsending, always20 min → 3 min a messageone agentproposed (step 5)
W5Log what was sent and what came backthe compose sheet closing with Send; the email cell's mailbox twin, opened in ImportP sends from the system's Mail or Messages sheet; A0 marks the draft sent and logs an interactionthe draft, sent; an interactionthe person pressing Send5 min → 0in the appunverified: sending and logging built (step 5); reading the twin built (correspondents, threads, replies owed), on an invented twin only
W6Make an introduction"you should talk to this person", typed or saidA1 extraction; A0 double opt-in; A1 drafts to each side; Pan introduction; two draftsasking each side first; every email30 min → 5 minone agentproposed
W7Debrief a meeting by voicea VoiceDebrief note, or a recording in the appA1 SpeechAnalyzer transcript; A1 Foundation Models, one question at a time; A0 matcheran interaction, follow-ups, introductionsevery proposal20 min → 3 minin the appproposed
W8Merge duplicates and add sourcesa new batch; weeklyA2 agent proposes merges; A2 a separate agent enriches from public pages, each value with its source; Pchanges to people and organisationsevery merge; every new value3 hours a week → 20 mina few sessions (two roles, one lane)proposed (step 6)
W9The team's weekly pipelineMonday morningA0 counts by stage and owner; A1 a short summary; Pnone in the CRM; a digest draftsending the digest2 hours → 15 minone agent, woken by a scheduleproposed
W10Our own fleet as recordsmessages on our lanesA0 lane reader: an agent is a person record, a team an organisation, a lane message an interaction, a hand-over an introductionpeople, interactions, introductionsadding an agent the team has not seennot done todayone agentproposed (step 7)
W11What the agents are doingthe agents vault, read every 30 seconds while the screen is openA0 read the conductor's report; A0 group by project, the stuck first, who talks to whom, the latest messages; P sees what waits on them (answering through a lane is next)nothing yet: it only readsevery decisionnot done todaynative first (read only); a richer view as a vault appunverified: reading built, CI is the test, not tried on a device
W12Exchange keys by QRtwo people, two phonesA0 my contact card as a QR code; A0 scan and check theirs; P confirm it is them; A0 their key on their record in the CRM; next, A0 seal a vault key or a message to ita person with their keyconfirming who they are10 min → 30 sin the appunverified: cards and keys built, CI is the test, not tried on a device; sealing to a card is proposed
W13Read and answer your mailsigning in with Google on the deviceA0 sign in on Google's own page (OAuth with PKCE, the token in the Keychain); A0 read the inbox from Gmail and mark who is in the CRM; P read, reply or write, press Send and confirm; A0 send through Gmail as the person and log it on the CRM people it went toan interaction for mail sent to CRM people; a person added from a messageevery send and every person addedan inbox in the CRM instead of beside itin the appunverified: built, CI is the test; needs the owner's iOS OAuth client, not tried on a device

Later: the sync to Twenty (an A0 cell, for a classic CRM screen), and the email agentic cell feeding W5.

Plays that use them

What the app does today

W1 is built: the cells are Sources/Import/ (readers, the team CRM layout, vaults of vaults, the matcher, the planner), CardPhotoReader (Vision), Engine/CRMVault.swift (the signed commit), and the review screen (the person cell). Each cell has its own unit tests on invented people. What the next steps of the brief build fall into W3 (step 4), W4 and W5 (step 5), W8 and W10 (steps 6 and 7). The app's Workflows section lists the thirteen with their cells and whether each is built (Model/CRMWorkflow.swift), and a test holds it to this page and the reality file: only W1, W3, W5, W11, W12 and W13 are built, every workflow that changes records has a person cell, and no cloud model or agent cell runs in the app.

Explorers and villagers

A workflow can run as a vault app inside the CRM before it is built into the app, and a switch per section chooses which one runs: see vaults are the explorers, the app is the villagers.

What this does not claim