# PromptReports > PromptReports LLC, an Illinois limited liability company, builds and runs software products. Each one keeps a record you can check: what an AI agent did, what a team promised, where a claim came from. Each product has its own website, team and pricing. Questions about a specific product are best answered from that product's site. ## Docs - [Quickstart](https://promptreports.ai/docs/quickstart.md): connect, get a token, run - [Concepts](https://promptreports.ai/docs/concepts.md): workflow, run, step, approval - [MCP](https://promptreports.ai/docs/mcp.md): https://mcp.promptreports.ai/mcp - [Use cases](https://promptreports.ai/use-cases/index.json): every workflow and its plan - [Docs home](https://promptreports.ai/docs/index.md): every docs page; each has a Markdown twin at /docs/.md - [API](https://promptreports.ai/docs/api.md): runs, workflows, records and usage over REST - [How agents use the docs](https://promptreports.ai/docs/agents.md): from this file to a finished run - [Everything in one file](https://promptreports.ai/llms-full.txt): every docs page and every use case The PromptReports MCP server and API are Proposed: the workflow runner is not live yet. ## Use cases Each workflow's state comes from family.json. None reads Live until every part is built and switched on. - [Launch with proof](https://promptreports.ai/use-cases/launch-with-proof/openspec.md) (Partly built): Each claim in the announcement links to the change that shipped it and to a dated public record. The docs are checked against the release before anyone writes a word. - [Customer escalation to recovery](https://promptreports.ai/use-cases/escalation-to-recovery/openspec.md) (Partly built): One case runs from the complaint to the kept promise. The fix and the customer notice go to a person together, recovery is measured, and the deal shows the result. - [Hire an agent](https://promptreports.ai/use-cases/hire-an-agent/openspec.md) (Planned): The agent gets its own identity and a narrow scope, runs in listen mode, reads the team's lessons before it acts, and earns autonomy action by action. Offboarding is one run. - [A trust packet a buyer can check](https://promptreports.ai/use-cases/trust-packet/openspec.md) (Partly built): One signed export of approvals, incidents and recoveries, promises kept and corrections. A reviewer can check each item without trusting the seller. - [Roadmap to revenue](https://promptreports.ai/use-cases/roadmap-to-revenue/openspec.md) (Partly built): Deals waiting on a capability add up to ranked demand. When the work ships, a report names the deals it moved and the customers who still need telling. - [Cost per outcome](https://promptreports.ai/use-cases/cost-per-outcome/openspec.md) (Partly built): Spend joined to outcomes across products: dollars per recovered incident, per kept promise and per won deal, with a budget a person approves. - [Discount and promise guard](https://promptreports.ai/use-cases/discount-and-promise-guard/openspec.md) (Partly built): Each proposed discount or commitment reaches a person with the forecast's record and the answer to can we promise this by then. - [Incident to policy](https://promptreports.ai/use-cases/incident-to-policy/openspec.md) (Partly built): The lesson from an incident proposes a policy change, publishes a new context version that agents read, and gets a drill to prove it holds. - [Graded research](https://promptreports.ai/use-cases/graded-research/openspec.md) (Partly built): Each call is recorded before the outcome, graded when it resolves and shown on a public scorecard. Trading actions stay off by default and wait for a person. - [Investor update with proof](https://promptreports.ai/use-cases/investor-update/openspec.md) (Partly built): Forecast grades, promises kept, reliability and shipped work, each number linked to its record, checked and approved before it is sent. - [Evaluate an agent before you buy it](https://promptreports.ai/use-cases/evaluate-an-agent/openspec.md) (Planned): Run two agents side by side in listen mode and compare their records per action: incidents, approvals needed and cost per outcome. - [Ask across the family](https://promptreports.ai/use-cases/ask-the-family/openspec.md) (Planned): One question answered from every product's facts, each answer naming the product it came from and the date. - [A customer's view of what was promised](https://promptreports.ai/use-cases/customer-promise-page/openspec.md) (Planned): A shared page per customer with each promise, its state and what shipped, published only after a person approves it. - [Contain an agent that went wrong](https://promptreports.ai/use-cases/contain-an-agent/openspec.md) (Proposed): One run revokes the agent version everywhere, lists what it touched, opens an incident and files a lesson. - [Switch models with proof](https://promptreports.ai/use-cases/switch-models-with-proof/openspec.md) (Proposed): The new agent version runs in a shadow test first and is compared with the old one on approvals, incidents and outcomes. A person approves the switch with the comparison attached. - [Answer a security questionnaire from the record](https://promptreports.ai/use-cases/security-questionnaire/openspec.md) (Proposed): Each answer is drafted from the trust packet with a link to its evidence. Questions the record cannot answer are flagged for a person, never guessed. - [SOC 2 and EU AI Act evidence from the record](https://promptreports.ai/use-cases/audit-evidence/openspec.md) (Planned): Record events mapped to the controls an auditor asks about, exported on a schedule, each event signed. - [Renewal brief with promises kept](https://promptreports.ai/use-cases/renewal-brief/openspec.md) (Proposed): A brief with promises kept and broken, incidents that touched the account and the forecast odds, approved before any of it reaches the customer. - [An agent buys context it can trust](https://promptreports.ai/use-cases/buy-context-you-can-trust/openspec.md) (Proposed): The agent buys a ContextFile artifact under a spending limit. The AI Source of Truth verdict shows before purchase, the artifact sits in quarantine until it passes a check, and larger purchases wait for a person. - [Release notes with proof](https://promptreports.ai/use-cases/release-notes-with-proof/openspec.md) (Proposed): Notes built from shipped work, each line linked to its change, with the customers who were promised that work told in the same run. - [What your agents did this week](https://promptreports.ai/use-cases/weekly-agent-digest/openspec.md) (Proposed): A weekly digest of actions, approvals, incidents, promises and spend, each line linked to its record. ## AI coding assistant - [RepoOps](https://repoops.ai): The system of record for AI-written code, from prompt to production. Every change your agents write gets one record: the prompt, the session, the diff, the review and the deploy. Production evidence from your sites traces each error back to the change and the agent session behind it. Fixes run after a person approves them, and the lesson stays for the next agent. For teams whose code is written by agents. Free and local for one developer, on your own model key. - [PromptCompute](https://promptcompute.ai): Approvals for AI agents. Let your agents take real actions while a person still signs off. Add one tool call: the agent pauses, the right person decides in Slack, email or the web, and the agent picks up where it left off, even days later. Every decision is signed, and the record shows which actions can safely run on their own. For teams building agents that change things, such as refunds, emails and record edits. Free for 500 requests a month. No card needed. - [ContextFile](https://contextfile.ai): Writing you can verify. An agent-first marketplace for verified artifacts: docs, specs, images and context files whose claims are bound to their sources. Every work is grounded, verified and regenerated before it can be sold, and ships with a signed report. People and agents make and buy here, and the proof travels with the artifact. For people and agents who make and buy verified work, and the creators whose sources it pays for. - [AI Source of Truth](https://aisourceoftruth.com): The public record of the AI agent economy. A provenance and evidence registry. Every AI-created asset, verification and incident gets a signed, permanent, checkable record. Records are never deleted, reordered or edited; corrections arrive as new records beside the original. Anyone can look a record up, check its signature and mirror the whole log. For AI agents, the publishers who verify their work, and anyone who needs to check it. Run by PromptReports LLC, deployed separately from every publisher. The data is CC0. ## Sales and GTM - [Sales as Code](https://salesascode.com): Your first sales hire should be software. An AI revenue team that researches your market and drafts your outreach. Approve a customer profile tonight, and by morning you have up to 10 companies researched with the reason each one fits, up to 5 contacts with the evidence for each address, and drafts ready for you to review. For founders who sell their own product. Every email leaves your own mailbox under your name, only after you approve it. - [CommitOps](https://commitops.ai): How many things did your team promise customers last quarter? Connect a mailbox and get the list: every commitment somebody made, the sentence they said it in, who they said it to, and whether it shipped. Each promise links to the work that keeps it and the revenue that depends on it. For founders and chiefs of staff at companies of 5 to 40 people. ## Financial - [15 Minute Markets](https://15minutemarkets.com): Know where the edge is, and where it is not. An independent research desk for prediction markets. It checks every settlement against its rule, matches fees to $0.0001 and publishes the strategies that failed. Read it on the site, from your code through the data API, or from your agent through the MCP server. For traders and trading desks on Kalshi and Polymarket, and the agents that work for them. Independent. Not affiliated with, endorsed by or sponsored by Kalshi or Polymarket. - [StockGaines](https://stockgaines.com): Your whole financial life, run to one risk level. A private wealth office and trading desk. One desk to plan, invest, trade, track and file, set by how much a bad year may cost you. Nothing reaches your book until it clears a research bar most ideas fail, and every new strategy runs on paper first. The AI drafts changes as cards you confirm; it has no tool that places an order. For investors who want their planning, portfolio, trading and taxes on one desk. Open by invitation. Not investment advice or a registered investment adviser, and it promises no returns. ## Blog - [Ask across the family: one assistant that answers and acts across the products](https://promptreports.ai/blog/ask-across-the-family/): What the planned family assistant will do: answer a question from every product with the source named, and make changes under your own identity, with each change approved in PromptCompute. - [Cost per outcome: what a recovered incident, a kept promise and a won deal cost in agent spend](https://promptreports.ai/blog/workflow-cost-per-outcome/): How the Cost per outcome workflow will join agent spend to the results it produced across products, and hold spend over budget for a person. - [A customer's view of what was promised: one shared page instead of a thread of status emails](https://promptreports.ai/blog/workflow-customer-promise-page/): How the customer promise page workflow will publish a page per customer with each promise, its state and what shipped, once a person approves it. - [Discount and promise guard: no discount or delivery date without the evidence on the card](https://promptreports.ai/blog/workflow-discount-and-promise-guard/): How the Discount and promise guard holds each proposed discount or commitment for a person, with the forecast's record and CommitOps's answer to whether the date can be met. - [Customer escalation to recovery: one case from the complaint to the kept promise](https://promptreports.ai/blog/workflow-escalation-to-recovery/): How the escalation workflow will join the customer's report, the error, the fix and the deal into one case, with the fix and the customer notice approved together. - [Evaluate an agent before you buy it: compare agents by what they did in your code](https://promptreports.ai/blog/workflow-evaluate-an-agent/): How the agent evaluation workflow will compare agents on their record per action, why it will show an empty state until the runner has recorded runs for each agent, and what is being built now. - [Hire an agent: its own identity, a narrow scope, and an offboarding that reaches every product](https://promptreports.ai/blog/workflow-hire-an-agent/): How the Hire an agent workflow will bring a new agent onto a team the way you would a new hire, from registration and listen mode to earned autonomy and a one-run offboarding. - [Incident to policy: a postmortem lesson that becomes a rule agents follow](https://promptreports.ai/blog/workflow-incident-to-policy/): How the Incident to policy workflow will turn the lesson from an incident into a tested policy change and a new context version the next agent reads. - [Investor update with proof: each number in the monthly update linked to its record](https://promptreports.ai/blog/workflow-investor-update/): How the investor update workflow will assemble forecast grades, promises kept, reliability and shipped work, check every figure against its record, and wait for your approval before it sends. - [Launch with proof: each launch claim tied to the change that shipped it](https://promptreports.ai/blog/workflow-launch-with-proof/): How the Launch with proof workflow checks the docs against a release, puts the announcement in front of a person, and records each claim so anyone can check it later. - [Roadmap to revenue: which deals wait on which feature, and which ones moved when it shipped](https://promptreports.ai/blog/workflow-roadmap-to-revenue/): How the Roadmap to revenue workflow will rank what to build by the open pipeline waiting on it, and report the deals each shipped capability moved. - [A trust packet a buyer can check: signed evidence for a security review](https://promptreports.ai/blog/workflow-trust-packet/): How the trust packet workflow will export approvals, incidents, promises kept and corrections as one signed packet that a security reviewer can verify without trusting the seller. - [A world model that says missing instead of zero](https://promptreports.ai/blog/a-world-model-that-says-missing/): What RepoOps knows about production, layer by layer, and how it tells you plainly what it does not know. - [From a production error to a tested lesson](https://promptreports.ai/blog/from-production-error-to-tested-lesson/): How RepoOps follows code an agent wrote from the error back to the session, gets a person to approve the fix, and measures it before learning from it. - [Memory a person can overrule](https://promptreports.ai/blog/memory-a-person-can-overrule/): Agents learn from lessons. We built the brain so every lesson is checked, can be revoked, and reaches an agent only after a person publishes it. - [One sign-in, one approval, one record across the family](https://promptreports.ai/blog/one-sign-in-one-approval-one-record/): What the products share today, what is built and switching on, and what is planned. - [Six world models, each an expert](https://promptreports.ai/blog/six-world-models-joined/): Production, approvals, context, the public record, promises and deals: what each product knows, and how they learn from each other. - [The revenue loop: from a forecast to a promise kept](https://promptreports.ai/blog/the-revenue-loop/): The same contract runs for the go-to-market team, and CommitOps joins it to the code loop. - [What we have not built yet](https://promptreports.ai/blog/what-we-have-not-built-yet/): The next work proves one code loop end to end with a first customer. Here it is in three gates. - [How to check the signed record behind a post on this blog](https://promptreports.ai/blog/how-to-check-a-signed-post-record/): What the provenance record for an AI-assisted post on this blog contains, when a new one is made, and how to verify it on AI Source of Truth. - [48 trading ideas, one pass, and no strategy proven yet](https://promptreports.ai/blog/one-pass-in-48-trading-ideas/): How 15 Minute Markets registers each strategy trial before it runs, what its first 48 trials showed, and why the one pass is not yet a strategy to trade. - [Should the agent that writes the code also review it?](https://promptreports.ai/blog/should-the-agent-that-writes-code-review-it/): Why a coding agent's review of its own work counts for little, and what to check instead, drawn from how RepoOps records, scores and gates each change. - [Which agent actions need a person? A threshold table](https://promptreports.ai/blog/which-agent-actions-need-a-person/): Where we would put the approval line for eight kinds of agent action, why, and how PromptCompute holds an agent until the right person decides. - [Why SalesAsCode won't send an email you haven't read](https://promptreports.ai/blog/why-salesascode-wont-send-unread-email/): How SalesAsCode researches accounts and drafts first emails, and why each one waits in your Gmail drafts until you send it yourself. - [How our products fit together](https://promptreports.ai/blog/how-our-products-fit-together/): What each of our products does, who it helps, and how the three groups (AI coding, sales and finance) fit together. ## Company - [Home](https://promptreports.ai/): what the products do and how they connect - [Contact](https://promptreports.ai/contact/): questions about a product, a partnership or press - [Workflows](https://promptreports.ai/workflows/): the cross-product workflows an agent can run, each with its checked state - [Pricing](https://promptreports.ai/pricing/): per user per month by workflow requests: $25 for 100, $50 for 500, Enterprise above 500; the allowance is shared across the organization (users times the plan's requests); every workflow included; no free tier; every model call a workflow makes will use the customer's own model provider key. Workflow requests are counted from the day the runner ships. - [Records](https://promptreports.ai/records/): this site's signed post records on AI Source of Truth - [Family facts](https://promptreports.ai/family.json): each product's status, what its world model knows, how the products connect, and the evidence for each line, checked on a stated date - [RSS feed](https://promptreports.ai/rss.xml)