Ten31 Venture CRM + Agentic System — AGENTS.md

The foundation is a self-hosted venture-fund CRM — a purpose-built fundraising tool that replaced Airtable to (1) keep sensitive LP/prospect data off third-party servers, (2) drop subscription cost, and (3) fit the fund's workflow: managing ~150 existing LPs, tracking 250+ prospects, and running the capital-raise pipeline. Core CRM domain: contacts (investor/prospect/advisor), organizations, opportunities (the deal pipeline), and communications; investor commitments live in the canonical fundraising_* grid (the legacy single-fund lp_profiles table was retired in v0.1.0:78). The fund (Ten31, ~$200M AUM, bitcoin/energy/AI thesis) runs it on a Start9 box, accessed over ClearNet (StartOS StartTunnel) with app-level user auth by a team of ~5 (Tailscale is not in use). Schema/API tour: docs/crm-overview.md.

The agentic system is new functionality built on top of that CRM — an in-house AI layer to widen the fundraising funnel, sharpen the thesis, and automate outreach drafting. Frontier reasoning runs on Claude (Agent SDK/API); privacy-sensitive and bulk work runs on local DGX Spark models via the Spark Control gateway. Phase 0/1 — no live outward-facing agents; agents draft, humans send.

Inbox check: At session start, if ~/Projects/standards/INBOX.md exists, scan it for items tagged (CRM) and surface them before proposing next steps; triage with /triage.

Stack (versions that matter)

Python 3.11, standard library only at runtime. The CRM is one monolith, backend/server.py (~5k lines): a stdlib http.server.ThreadingHTTPServer + hand-written CRMHandler with manual path dispatch (do_GET/do_POST). Not FastAPI. backend/requirements.txt lists FastAPI/SQLAlchemy/Alembic/Pydantic/pytest-style deps but none are imported at runtime (vestigial).
SQLite at data/crm.db (WAL, foreign_keys=ON), opened per-request via get_db(). Schema via ordered migrations.
Frontend: single frontend/index.html, inline-Babel React. No build step.
Optional runtime deps, used only if present: bcrypt, PyJWT (jwt), cryptography (Gmail module).
MCP + ingest (in the Docker image, not the bare CRM): mcp==1.2.0 (FastMCP, backend/mcp/server.py), fastembed==0.4.2, anthropic, cryptography==42.0.5.
Packaging: StartOS 0.4, TypeScript SDK (@start9labs/start-sdk) under start9/0.4/startos/. Live target is start9/0.4/.
Local models (bge-m3 embeddings, bge-reranker-v2-m3, /api/search, Qdrant): always via Spark Control. Contract: docs/EMBEDDINGS.md.

Commands

# Run locally (dev, port 8080; or ./start.sh <port>) — runs python3 backend/server.py
./start.sh
# Run prod-mode (beta) — requires CRM_SECRET_KEY
./start_beta.sh
# Sanity-check edits (there is no compiler/build for the CRM)
python3 -m py_compile backend/server.py
# Run ONE test (tests are standalone scripts with `if __name__ == "__main__"`; no pytest installed)
python3 backend/redaction/test_scrub_leak.py        # substitute any backend/**/test_*.py
# Run all tests (aggregate runner — runs each backend/**/test_*.py in its own subprocess)
python3 backend/run_tests.py                         # add substrings to filter, e.g. `... soft_delete redaction`
# Build + install the s9pk — BUMP THE VERSION FIRST. See docs/guides/packaging.md.
cd start9/0.4 && make

Migrations apply automatically at startup (backend/core_migrations.py, schema_migrations ledger). See docs/guides/migrations.md before adding one.
Lint: none configured.

Directory layout (day-one)

backend/server.py — the CRM monolith: HTTP handler, route dispatch, init_db(), auth (username/password → HS256 JWT, roles admin/member/bot).
backend/core_migrations.py + backend/migrations/NNNN_*.sql (+ paired .down.sql) — additive schema migrations, applied at startup.
backend/thesis_seed.py — Thesis Workshop seed + idempotent ensure_* one-time seeders, wired in server.init_db().
backend/thesis_review.py — thesis version review/approval (human dual sign-off → canonical).
backend/mcp/ — architect_agent.py (Claude thesis copilot), architect_tools.py, outreach_agent.py (LP draft assistant), architect_grounding.py, crm_tools.py, server.py (FastMCP).
backend/email_integration/ — Gmail capture via domain-wide delegation + Tier-B draft creation (compose.py).
backend/redaction/ — scrub.py + client.py: the scrub→Claude→re-hydrate privacy boundary.
backend/ingest/ — chunk→embed→Qdrant + retrieval modes.
backend/entity_*.py — entity resolution/merge (the two-investor-model reconciliation).
backend/nl_query/ — read-only natural-language query (W2): intents.py (curated parameterized query catalog), runner.py (slot validator = trust boundary), translate.py (local-Qwen question→{intent,slots}). See the nl-query guide.
backend/matrix_intake/ — Matrix intake bot (separate process; matrix-nio, isolated to this component): typed message → local-Qwen parse → in-thread approve → write via the CRM's own log-communication. See the matrix-intake guide.
frontend/index.html — the entire UI.
docs/ — architecture, phase plans, contracts, runbooks (see Deeper docs). docs/guides/ — scoped subsystem rules (see below).
start9/0.4/ — StartOS package (startos/utils.ts holds PACKAGE_VERSION).
data/crm.db — the live DB (gitignored). .env / .env.example — config (.env gitignored).

Scoped guides

Subsystem rules live in docs/guides/ and lazy-load in Claude Code via .claude/rules/ symlinks (scoped by paths: frontmatter). Read the guide before editing that area:

Migrations or seeders (backend/migrations/, core_migrations.py, thesis_seed.py) → docs/guides/migrations.md
Thesis logic (backend/thesis_*.py, backend/mcp/architect_*.py) → docs/guides/thesis.md
Redaction or any MCP/Claude path (backend/redaction/, backend/mcp/) → docs/guides/redaction.md
Ingest / retrieval (backend/ingest/) → docs/guides/spark-ingest.md
Email capture / drafts + digest send (backend/email_integration/, backend/digest_mailer.py, backend/smtp_send.py) → docs/guides/email.md
Building or deploying the s9pk (start9/) → docs/guides/packaging.md
Matrix intake bot (backend/matrix_intake/) → docs/guides/matrix-intake.md
Natural-language query (backend/nl_query/) → docs/guides/nl-query.md

Conventions

Investor model — the grid is canonical (since v0.1.0:78). The fundraising_* grid is the system of record: an investor entity (row) → many contact "pills" → per-fund commitments. The classic contacts table is a read-only per-person directory, auto-populated from the grid — create/edit people in the grid, not the Contacts page. Email capture rolls multiple people up to one investor. The legacy single-fund lp_profiles model is retired (empty table kept, per never-hard-delete). Reconciling grid ↔ classic contacts to canonical IDs is the core entity-resolution task — see docs/crm-overview.md.
Soft-delete only: deleted_at and/or status='retired'; never hard-delete. Every READ path must filter deleted_at IS NULL — list handlers, get-by-id, nested related-data sub-selects, and aggregate sub-selects (COUNT/SUM/MAX). Audits found leaks in all of these (2026-06-12 detail + nested; 2026-06-13 list-view contact_count/total_funded/comm_count); the opportunities/pipeline aggregates were fixed in v0.1.0:87 (handle_pipeline_report + dashboard pipeline metrics now filter deleted_at), but the reports subsystem's communications-side aggregates (dashboard recent_comms/comms_this_month/meetings_this_month, activity report) still leak (see Current state). Regression-guarded by backend/test_soft_delete_reads.py (+ test_reminders.py for the reminders read paths, incl. the recency rollup whose email-activity liveness signal is email_account_messages.deleted_at, not emails). (Thesis has a subtlety here — see the thesis guide.)
Env: secrets in .env (gitignored); names in .env.example. Verified names: ANTHROPIC_API_KEY, SPARK_CONTROL_URL, SPARK_CONTROL_VERIFY_TLS, QDRANT_URL, X_API_KEY, CRM_DB_PATH, CRM_DEV_DB_PATH. Also used: CRM_SECRET_KEY (beta/prod), CRM_HOST/CRM_PORT, CRM_DATA_DIR; digest mailer: CRM_DIGEST_SENDER (DWD impersonation sender) + SMTP_HOST/SMTP_PORT/SMTP_SECURITY/SMTP_FROM/SMTP_USERNAME/SMTP_PASSWORD (SMTP fallback); daily digest (Phase B): CRM_DIGEST_ENABLED + CRM_DIGEST_SEND_HOUR only seed the first-boot default — the live control is the DB policy (app_settings.digest_policy, set in Settings → Admin).
Config placement: operational/feature toggles live in the admin panel, DB-backed via app_settings (read-merge through a load_*_policy(conn) helper shared by the API + any scheduler; precedence DB-row → env-seed → default), so they're discoverable and take effect live. Reserve StartOS actions / env for secrets and deploy-time config (SMTP creds, API keys, DWD sender). Precedent: digest_policy (GET/PATCH /api/admin/digest/policy), fundraising_backup_policy.
Agent/bot API access — three roles now (admin/member/bot). require_admin is the only hard gate; everything else is "authenticated" (member, admin, and bot all pass). The bot role (added v0.1.0:89) is authenticated-but-never-admin: require_bot_or_admin gates agent-facing endpoints (e.g. /api/intake/email-proposals*) so a bot credential reaches only what it needs, never user-management/settings/security. Provision it via Settings → Admin edit-user dropdown (kept out of the teammate-invite form). Two axes to keep separate as more agent capability lands: the role controls reach (which endpoints); the per-feature human draft→approve gate controls autonomy (acting unattended). Money/merge/delete mutations stay behind the approval gate regardless of role. Don't build a finer capability/scope system until real NL-mutation endpoints exist to scope against.
Design: before building or changing any user-facing UI, read design/DESIGN.md and design/tokens.tokens.json and conform to them. The mobile-first redesign landed (Claude Design round-trip distilled into the contract 2026-06-19): the authority for mobile/responsive work is DESIGN.md §8 + the tokens mobile and color.light groups; design/BRIEF.md is the input brief and design/_imports/2026-06-19/ the provenance + per-surface interaction reference (the comps are Claude Design runtime prototypes — re-author each surface in the app's React idiom + real API, not drop-in). A light theme is adopted as a planned, toggle-gated feature (dark stays default). (Note: inline style={{}} objects can't respond to media queries; responsive layout belongs in the CSS <style> block — and the inline-style→CSS migration is the unscoped prerequisite gating mobile implementation, see ROADMAP.md.)
Commit style: imperative subject, concise body explaining the why; put the package version in the subject (… (v0.1.0:NN)) for shippable changes. No AI co-author / attribution trailers — commits are authored by the user.

Always

Verify before shipping: python3 -m py_compile the edited files; for DB logic, run the change against a copy of data/crm.db, never production.
Keep real LP data out of Claude: develop only on code/schema/synthetic-or-locally-redacted data; route any real record substance through backend/redaction first.
Get explicit user authorization before any production deploy/install to $START9_BOX_HOST.

Never

Never treat Qdrant (or any derived index) as source of truth — the CRM/SQLite is canonical and rebuildable-from.
Never hard-delete CRM records or thesis history — soft-delete/archive only.
Never let an agent send email, post, or contact an LP autonomously — agents draft; a human approves and sends.
Never set a thesis_version canonical from code/seeds — that is human dual sign-off.
Never call a Spark directly — go through Spark Control (SPARK_CONTROL_URL).
Never commit secrets, data/crm.db, .env, or data/backups/ (all gitignored). Scan staged files before committing. (.claude/ is tracked — launch.json and rules/ symlinks ship with the repo; keep local-only settings in .claude/settings.local.json.)
Never bulk-export the LP list to any third party; send only minimal non-sensitive context to Claude.
Never assume FastAPI / SQLAlchemy / pytest are in play — they sit in requirements.txt unused; runtime is stdlib + SQLite.
Never add a Co-Authored-By / "Generated with" trailer to commits or PRs — commits are the user's.

Deeper docs

Full constitution + guardrails: docs/ten31-constitution.md
Architecture & rationale: docs/Ten31_Agentic_Build_Plan.md
Retrieval/embeddings contract: docs/EMBEDDINGS.md
CRM schema/API tour: docs/crm-overview.md
Current thesis handoff: docs/thesis-handoff.md
Operations & runbooks: docs/OPERATIONS.md, docs/go-live-runbook.md, docs/gmail-enablement-runbook.md

Current state

Phase 0 + Phase 1 built; box + repo live at v0.1.0:94 (main ahead by docs/design-only commits since). The fundraising grid + email capture is the canonical system of record. Active threads: mobile-first redesign (design DONE → implementation planning next) and W2 NL query (live; web "Ask" box outstanding). History: git log + start9/0.4/startos/versions/; backlog/debt: ROADMAP.md / EVALUATION.md.

Mobile-first redesign — design phase COMPLETE; implementation not started. This session ran the /design round-trip Phase C/D: distilled the Claude Design cloud output ("Venture-CRM mobile redesign") into the contract — DESIGN.md §8 (responsive) + §4 (mobile component states) + §3 (15px scale), tokens mobile group + color.light, provenance + per-surface interaction reference in design/_imports/2026-06-19/. Light theme adopted as a planned, toggle-gated feature (dark default). Comps are Claude Design runtime prototypes — re-author each surface in React against the real API, not drop-in. Process learnings pushed to standards/guides/design.md.
Built, deploy pending: drag-reorder grid views (frontend-only; moveViewBefore in index.html; persists via autosave → views_json; render-smoke green, browser-interaction untested).
W2 — NL query (read-only): LIVE (v93; matched-only fix v94). Local-Qwen translate → curated intents + slot validator (no generic SQL), POST /api/query/nl, audited; Matrix Q&A + intake ?/@bot live. Remaining: in-room human smoke + step-4 web "Ask" box. Guides: docs/guides/nl-query.md + matrix-intake.
W1 — reminders: LIVE (v93). Grid-tied tickler (migration 0006, /api/reminders, derived reminder_status, last_activity_at rollup). Deferred W1b = nurture-gap auto-suggested reminders (staleness nudge → Engaged/Diligence).
Done & live: email-proposal Matrix review + bot role (v91); grid-driven Pipeline (v88); Matrix intake bot; Gmail capture (DWD) + propose→approve + daily digest; Thesis Workshop + Architect (Claude, dual-approval); outreach drafts. All draft-only.
Tests: 35/35 backend green (python3 backend/run_tests.py), py_compile clean; render-smoke gates make. (Docs/design only this session — no code touched.)
Next (priority order): 1) mobile implementation plan — scope the inline-style→CSS migration first (responsive can't live in ~1300 inline styles, still unscoped); 2) land the locked pipeline-stages/flags data layer (enum + migration + Existing-Investor derive + staleness); 3) build the 4 mobile surfaces (Grid first; writes via one-row log-communication + pipeline link→stage, never whole-grid PUT; light theme co-lands with the CSS migration); 4) deploy view-reorder (next s9pk build); 5) W2 step-4 web Ask box + in-room smoke; 6) W3 bot grid-mutations behind Matrix gate; 7) W1b nurture-gap reminders; then P2 debt (reports comms-aggregate soft-delete sweep, ?limit=abc crash, auth regression test, oversized icon).
Open / risks: mobile implementation blocked on the unscoped inline-style→CSS migration; W2 translation only happy-path-validated; Claude/Architect path still unverified live on the box; v2.0 reserve-asset spine approved but not canonical (needs dual sign-off); doc drift — crm-overview.md + EVALUATION.md still call lp_profiles live.

16 KiB Raw Blame History