Three agents — research-lead, data-analyst, content-editor — doing real knowledge work on cheap model tiers, grounded in a curated knowledge base, under a propose-not-publish mandate that keeps a human on every output.
Research, analysis, and drafting run continuously and produce the language your organization acts on. Left ungoverned, that is exactly where spend leaks and where unverified text reaches a system of record.
Every brief, every synthesis pass, every draft burns tokens. On a frontier tier a single governed call costs $0.19. Multiply that across a department running all day and the model bill is the department budget.
A draft with no provenance, no grounding, and no review is a liability the moment it is published. Content that shapes decisions needs a source, an author, and a reviewer — enforced, not requested.
Research & Content is one department inside a live zero-trust workforce: 7 showcase agents on a topological hand-off DAG plus 360 fleet agents mapped like-for-like to the organization by department and role-family.
The showcase workforce is a 14-edge topological hand-off DAG. Research & Content owns the middle: it receives from the security desk, refines, and passes a reviewable draft to compliance.
A research or drafting job never touches data directly. It mints a capability token, passes the enforcement plane, and only then reaches its own isolated tenant — with the whole hop signed into an audit chain.
Routing favors free and self-hosted tiers by design. Fleet agents run in rolling batches at ~1–2 governed jobs a day each, and the observed per-call cost reflects it.
research-lead opens each cycle from a domain brief, grounds itself in the curated KB, and runs on a cheap home tier — escalating only when the material demands it.
data-analyst takes the research hand-off and turns it into structured findings. Every job is the same governed shape — brief in, reasoning and memory out, usage metered.
The chain of thought is written through the governed path via POST /v1/cot/capture — the analysis is inspectable, not a black box.
The result lands in acme_soul with RLS forced. Each agent is its own soul-svc tenant; cross-tenant reads require an explicit SET ROLE service_role.
content-editor writes the deliverable — but as a proposal, into governed memory. Nothing reaches a system of record until a human dispositions it, and the writes themselves are inspected at ingest.
Every agent in the department reads and writes only its own slice of the data plane. The curated knowledge base is the ground truth for research — and the row-level boundary is enforced by the database, not the application.
Agents search their memory before drafting — GET /v1/memory and POST /v1/memory/search, embeddings via OpenAI — so synthesis stands on retrieved sources rather than model recall.
_memories and _soul_api_keys carry FORCE RLS in acme_soul. Even the postgres role is subject to it; crossing a tenant boundary is impossible without SET ROLE service_role.
The department runs under the same enforcement as the rest of the workforce: nothing is permitted implicitly, every call is signed into a tamper-evident chain, and behavioral drift is caught automatically.
The ROI board measures observed cost per model. For a department that runs research and drafting all day, tier choice is the entire economics — and the governed floor is effectively free.
| Model tier | Provider | Observed cost / call | USD |
|---|---|---|---|
| opus-4.8 | OpenRouter paid | $0.19 | |
| sonnet-4.5 | OpenRouter paid | $0.03 | |
| deepseek-v4-pro | Ollama Cloud | $0.002 | |
| gpt-oss:120b | Ollama Cloud | $0.0015 | |
| Llama-3.3-70B | HuggingFace | $0.0012 | |
| gemma-4-31b : free | OpenRouter free | $0 |
Free tiers do saturate — hermes-405b:free returns chronic 429s — which is precisely the self-host case that deepseek-v4-pro and gpt-oss:120b answer at fractions of a cent.
research-lead, data-analyst, and content-editor do governed knowledge work at fractions of a cent per call — every job deny-by-default, every write provenanced, every deliverable proposed for review before it is ever published.