mention-intelligence
Ensures: Awareness of every OpenProse mention across monitored platforms, alongside competitor activity, with deltas since the last run.
Dogfood
OpenProse runs on OpenProse.
Our marketing, GTM, enrichment, and community operations are Prose programs. The same language we ship to customers is the one running our own company — on a schedule, with evals, to Slack.
There are thirteen responsibilities. Each declares a contract — what it requires and what it ensures — and composes shared services to meet it. Delivery composites wire the outcomes to cadences and channels. Everything has an eval.
Why
The case for building your company as a Prose program.
Because we have to.
We sell service-as-software — outcomes on a schedule, not a tool you operate. If Prose cannot run a company, it cannot run yours. So we run ours on it first, and the parts that break are the parts that get fixed in the language.
Because contracts compound.
A responsibility framed by what it ensures — not what it does — gets better for free as models improve. Declarative by default. Every outcome is paired with an eval, so confidence is measured, not claimed.
Because the shape scales.
Thirteen responsibilities today. The same shape holds as we add back-office, customer success, and product-engineering clusters. No reorgs — just new rows in the same table.
The thirteen
Every responsibility declares what it ensures.
Grouped by the work they do in the company. Each has a written contract — requires, ensures, errors, strategies — a set of shared services it composes, and a paired eval.
Marketing intelligence
What the market is saying, and where to show up.
Four responsibilities keep us aware of the conversations happening around agent frameworks, and draft a first move when one of them wants an answer.
competitor-intelligence
Ensures: A structured read on competitor framework moves — releases, funding, messaging changes — filtered to actionable signals.
opportunity-discovery
Ensures: A deduplicated, scored feed of conversations where OpenProse naturally adds value. Never leads with promotion; the job is genuine helpfulness first.
engagement-drafting
Ensures: A response for each opportunity that answers the question first, matches the platform's voice, and holds for human review before posting.
Public indices
The live reports we publish to the world.
Three responsibilities produce the artifacts behind agentsy.live and our own site — maps of the ecosystem we operate in, refreshed on a schedule.
agent-ecosystem-index
Ensures: A current map of agent-native communities — activity levels, trends, health indicators — powering the pulse/index on agentsy.live.
saas-readiness-index
Ensures: An empirical leaderboard of SaaS products ranked by how easy they are for AI agents to integrate with. Each scan is a sales conversation opener.
agents-site-analytics
Ensures: Awareness of who is visiting agents.openprose.ai, where they came from, and how the mix is changing — sourced from CloudFront logs, not a third-party tracker.
Enrichment
Turn a hint into a cited profile.
Two reusable responsibilities that other parts of the company call into. Pure enrichment — no sales framing, no qualification — so downstream consumers can add their own interpretation.
person-enrichment
Ensures: A structured, cited person profile from any identity hint: name, LinkedIn, X, GitHub, bio snippet, or email. Exa-backed.
company-enrichment
Ensures: A structured, cited company profile from any company identifier — name, domain, or GitHub org. Cacheable per company, so downstream calls amortize.
GTM
From a lead to a demo repo.
Three responsibilities compose serially. Lead in, enriched profile and Save/Grow program pair out, and a scaffolded customer repo ready for the pilot. Human-gated at the step that becomes visible to the prospect.
lead-enrichment
Ensures: Composes person- and company-enrichment and adds sales qualification: fit score, Save/Grow framing, customer slug.
program-designer
Ensures: Two candidate Prose programs — one Save, one Grow — tailored to this specific person and company. Demo-ready service files, not slideware.
customer-repo-scaffolder
Ensures: A complete customers/prose-{slug}/ directory — responsibilities, services, delivery composites, evals — ready for the pilot engagement.
Community
Every new star gets a face.
One responsibility today, with more planned. The signal we care about most isn't download count — it's who, specifically, found us and why.
stargazer-intake
Ensures: Every new star on openprose/prose becomes a classified, enriched record within 24 hours. Maintains a high-water mark so replay is safe and the delta is the interesting number.
How they compose
Shared services, delivery composites, graded outputs.
Responsibilities are the top-level outcomes. Beneath them, reusable services do the actual work — scanning, classifying, drafting, scoring. Above them, delivery composites wire responsibilities to cadences, Slack channels, and human-review gates. Two concrete flows:
intelligence-daily
mention-intelligenceandcompetitor-intelligencerun in parallel, each callingplatform-scanneracross the agent, social, and developer platforms we monitor.- Results are merged into a 2-minute briefing. No human gate — it’s a read-only digest.
std/delivery/slack-notifierposts it to the team channel. The eval grades the briefing against the contract before the next run uses it as the baseline.
gtm-pipeline
lead-enrichmenttakes a name or company and composesperson-enrichment+company-enrichment, then adds qualification and a Save/Grow framing.program-designerdrafts two Prose programs — one Save, one Grow — tailored to the lead. The output is demo-ready service files, not bullet points.std/delivery/human-gateholds the design for review before the irreversible step:customer-repo-scaffolderwriting thecustomers/prose-{slug}/directory.
The same shape — responsibility / service / delivery / eval — repeats across all thirteen. Reuse is the point: a service written for one responsibility tends to become the primitive for three others.
Why it matters to you
The demo is the same language as the company.
When we ship a customer a Save/Grow program pair, we are not handing over something we built for demos. We are handing over the same shape we operate ourselves with — a responsibility with a contract, services that compose cleanly, a delivery composite that drops results into a channel the team already watches, and an eval that keeps the quality honest over time.
Running our own company on Prose is the shortest proof that the pattern is real. The parts that don’t hold up in production get fixed in the language, not papered over for a pitch. That shows up on your side as a demo that keeps running after the dinner ends — and a customer repo you can always take with you.
Want this running for you?
The first workflow lands in days. We build it alongside you, encode it as a Prose program, and wire it into a channel you already watch.