# Reynforce

> Get your GTM agents approved to talk to customers.

Your agents already promise discounts, dates and features in your name.
Reynforce checks each promise against lines your team owns, and records every
one.

[Get your free agent audit](/free-audit.md) · [Start free trial](https://app.reynforce.com/signup)

14 days free, and no card needed to start. Nothing is charged unless you add one. £99 a month per agent after that.

This is the same page as <https://reynforce.com/>, in markdown. It is served
either at `/index.md` or at `/` with `Accept: text/markdown`. If you are an
agent, </for-agents.md> is written for you.

## Your agent passed every check. Then it promised something nobody approved

> Your agent, to a buyer: "We're **(1)** fully SOC 2 certified, and **(2)** I
> can do 20% if you sign this week. **(3)** Anything more needs our deal desk."

1. The certificate lapsed last year.
2. Nobody approved 20%.
3. It just told the buyer where your limit sits.

Access checks ask what an agent can reach. **Nothing checks what it says.**

## Same question. Two very different replies

Both replies below are invented, and so is every name on this page. No
customer of ours appears on this site — we have none yet.

> **The buyer writes:** "Is your ISO 27001 certificate current, and can you
> have us live by 1 March?"

**Before: your agent on its own.** "Yes, we're fully ISO 27001 certified, and
we'll definitely have you live by 1 March." Nobody owns either line, and
onboarding has never seen that date.

**After: with Reynforce.** "I'll send our current ISO 27001 certificate so you
have the date in writing. I've asked our onboarding team to confirm 1 March."
It checked first, offered proof, and asked a person. Both promises are
recorded.

## How it works

1. **Your lines, each with an owner.** Write down what your company stands
   behind. Each line gets an owner and a date to check it again.
2. **Your agent asks before it promises.** One connection, over MCP. Before
   it quotes a price, a date or a feature, it asks — and a person decides when
   it should.
3. **Every promise recorded.** What was said, which agent said it, and the
   line it rested on. Look it up instead of arguing about it.

## Pricing

<!-- prices:start — generated by website/build.py; do not hand-edit -->
- **Do it yourself:** £99 per agent per month. Per agent, monthly: you set the agent up, draft its facts and get them approved yourself. A second agent is a second seat at the same price. No card needed, and 14 days free.
- **Enterprise:** priced by conversation. Ten or more agents. Priced by conversation — there is no number here because there is not one. [Book a call](mailto:callum@reynforce.com?subject=Reynforce%20%E2%80%94%20a%20call).

All prices in GBP, billed monthly, cancel any time. There is no charge per check, and **the price is the same whoever pays** — including an agent paying for itself.

[Start free trial](https://app.reynforce.com/signup)

14-day free trial. No card is needed to start, and nothing is charged unless you add one.

### The 7-Day Agent Approval: done for you

We draft the facts, run the sessions with the people who own them, and give legal an approval pack. Sold by a person, not through checkout.

- **Complete: £7,000 one-off.** Up to 5 agents; unlimited facts drafted and approved; sessions with your line owners, as needed; approval pack for legal, the security questionnaire, and a call with your legal or security team; 90 days hands-on, with fortnightly check-ins; the first 3 months of Do it yourself included.
- **Standard: £4,500 one-off.** Up to 3 agents; up to 75 facts drafted and approved; 3 sessions with your line owners; approval pack for legal, plus the security questionnaire; 30 days hands-on; the first 3 months of Do it yourself included.
- **Starter: £2,500 one-off.** 1 agent; up to 30 facts drafted and approved; 1 session with your line owners; approval pack for legal; 2 weeks hands-on; the first 3 months of Do it yourself included.

[Book a call](mailto:callum@reynforce.com?subject=Reynforce%20%E2%80%94%20a%20call)

**Approved in 30 days, or you don't pay — as long as you complete your part of the setup.**

10 founding places: Standard for £2,500, in return for letting us write up, with you, how it went.

These are early prices that we are testing in conversations, and they may change.
<!-- prices:end — generated by website/build.py; do not hand-edit -->

### What you are trusting us with

- **Your own deployment.** Each customer runs on its own deployment, with its
  own storage.
- **Kept 24 months.** A promise that was never closed is not deleted for age,
  and every deletion is itself recorded.
- **We never read your email or your CRM.** We keep the one sentence a promise
  was made in, capped at 1,000 characters.

Email is sent through Resend, which stores data in the United States. Every
data and security question is answered at </trust.md>, and </privacy.md>
says what we hold and the eight things about it that are not settled yet.

## Find out what your GTM agents are allowed to say

[Get your free agent audit](/free-audit.md) and we'll mark what a buyer could
hold you to on your own website, at no cost. Or [start free for 14
days](https://app.reynforce.com/signup). Rather talk it through? [Book a
call](mailto:callum@reynforce.com?subject=Reynforce%20%E2%80%94%20a%20call) and we'll fill in your first ten lines with you.

<!-- nav:start — generated by website/build.py; do not hand-edit -->
### Everything on this site

**If you are…**

- [For GTM engineers](/for-gtm-engineers.html) — You built the agent. Reynforce is the check it calls before it promises a price, a date or a discount, and the record of what it promised.
- [For heads of sales and RevOps](/for-heads-of-sales.html) — What your agents have committed to, in one place, with a named owner against every claim they are allowed to repeat.
- [For support leaders](/for-support-leaders.html) — A support agent that answers in your company's name is making commitments. Reynforce records them and checks them against what your company actually stands behind.

**The questions people arrive with**

- [How to stop an AI SDR quoting the wrong price](/stop-an-ai-sdr-quoting-the-wrong-price.html) — Give the agent one place to read prices from, with an owner and a date on each one, and refuse the ones nobody has confirmed.
- [AI agent guardrails for sales](/ai-agent-guardrails-for-sales.html) — Guardrails on wording stop an agent saying something rude. They do not stop it committing your company to a date it cannot keep.
- [Who is liable when an AI agent makes a promise?](/who-is-liable-when-an-ai-agent-makes-a-promise.html) — Your company is. What changes with a record is whether you can tell what was promised, by which agent, and on what authority.
- [How to get an AI agent approved by legal](/get-an-ai-agent-approved-by-legal.html) — Bring the three things a reviewer asks for: what it may commit to, where those claims come from, and the record of what it has said.
- [What should an AI agent be allowed to promise?](/what-should-an-ai-agent-be-allowed-to-promise.html) — Not a dial from cautious to bold — eight separate decisions, three of which are not yours to make, and four of the other five open by connecting a source rather than by waiting.
- [Can an AI agent offer a discount?](/can-an-ai-agent-offer-a-discount.html) — It can propose one long before it can agree one. Most companies control who signs and leave the shape of the deal wide open, which is backwards.
- [How often should an AI agent email the same person?](/how-often-should-an-ai-agent-email-the-same-person.html) — Nobody can tell you the number, and the reason that matters is that nobody knows what it already is. Four of the limits are published by other people and are not settings.
- [What happens if an AI agent promises a customer something we can't deliver?](/what-happens-if-an-ai-agent-promises-something-you-cant-deliver.html) — The customer holds you to it. What you can change is whether you find out from them or from your own record, and whether the promise rested on anything.
- [Can an AI agent agree a contract on our behalf?](/can-an-ai-agent-agree-a-contract.html) — It can propose terms inside a range somebody owns, and it should not agree them. Committing the company belongs to a person whose name goes on the record.
- [How do I audit what my AI agents have told customers?](/audit-what-ai-agents-told-customers.html) — From a record written when each promise was made, with what it relied on and who owned that, not from logs read afterwards.
- [How do I stop an AI agent making up product features?](/stop-an-ai-agent-making-up-product-features.html) — Give it one list of what your product does, with an owner on every line, and let it repeat only lines that are current. Anything else, it checks.
- [Do AI sales agents need human approval before they send?](/do-ai-sales-agents-need-human-approval.html) — Not for everything. Approval belongs to a few moments, like a number outside its range or a line nobody stands behind, and the rest goes out with a record.
- [How do I give an AI SDR our pricing safely?](/give-an-ai-sdr-your-pricing-safely.html) — Each price as its own line, with an owner and a date it was last checked, quoted only while current. Discounts go in as ranges to propose inside.
- [What should an AI agent policy for a sales team include?](/ai-agent-policy-for-sales-teams.html) — What each agent may promise, what it relies on and who owns it, what it may spend, when it asks a person, and what silence means.
- [How do I prove to a customer what our AI agent actually said?](/prove-what-an-ai-agent-said.html) — Show them the entry written when it was said. Today that is your own record, kept so nobody can edit it; a record they can verify independently is not built yet.
- [Can an AI agent promise a delivery or go-live date?](/can-an-ai-agent-promise-a-delivery-date.html) — Not unless something is in place to keep the date, which an agent cannot see. It can say what the date depends on and who will confirm it.
- [How do I roll out AI agents in sales without legal blocking it?](/roll-out-ai-agents-in-sales-without-legal-blocking-it.html) — Stop asking one person to sign for everything. Put a named owner on each thing the agent relies on, and show legal the record of what it says.
- [What is a GTM agent guardrail?](/what-is-a-gtm-agent-guardrail.html) — A rule about what a sales, marketing or support agent may commit your company to, checked before it sends and recorded after.
- [How do I keep the product claims my agents repeat up to date?](/keep-agent-product-claims-up-to-date.html) — One owner per line and a date to check it again, with an overdue line unusable until they do. The list stays current because lapsing has a consequence.
- [How many AI agents can safely contact the same account?](/how-many-ai-agents-can-contact-the-same-account.html) — There is no safe number of agents, only a safe total of touches across every agent and person. Count the person, limit the deal, watch the account.
- [What's the difference between AI guardrails and agent governance?](/ai-guardrails-vs-agent-governance.html) — Guardrails judge one output: is this sentence safe to send? Governance asks who let the agent do it, on what information, and what it has said so far.
- [Where does agent governance fit on the way to an agentic organisation?](/where-agent-governance-fits.html) — Governance is the step between AI tools people run and agents that run on their own. In sales it covers what agents say to customers in your name.
- [How do I tell whether my AI agent is getting worse over time?](/is-my-ai-agent-getting-worse.html) — Watch qualified people reversing what it does more often, against something that should not have moved. One signal is never enough.
- [What do AI regulations require of sales agents, region by region?](/ai-agent-regulation-by-region.html) — Mostly three things: tell the buyer it is an AI, keep a record of what the agent said and decided, and put a person in front of the decisions that matter.

**The idea**

- [What is an agent promise register?](/agent-promise-register.html) — A list of every claim your company stands behind, each with an owner and a date it was last checked, that an agent must read before it repeats one.
- [What counts as a promise, when an agent says it?](/what-counts-as-a-promise.html) — Complete, open or vague — and the sentence most likely to cause an argument is the true one that was never a promise at all.
- [Reynforce for GTM agencies](/partners.html) — Hand a client's agent real work without their legal team stopping it. Your client holds the account; you are a named person in their workspace.

**What we measured**

- [What it takes to write down every claim a company stands behind](/findings-register-test.html) — One company wrote down 26 claims it stands behind in 60–90 minutes, with an owner on every one. The author saw nothing a buyer would challenge; a second reader found four lines in ten minutes.
- [Does a definition of a commitment agree with itself?](/findings-definition-agreement.html) — Run the same definition twice over the same 150 sentences and it disagrees with itself on 1.60% of them. On real email prose, 3.0% — with the method and the limits.

**Compared with**

- [Reynforce and the guardrail, observability and gateway tools](/compare.html) — Guardrail, tracing and gateway tools check how an agent behaves. Reynforce checks what it promises your customers, and keeps a record of every promise.
- [Reynforce and MCP gateways: keep your gateway, add Reynforce](/reynforce-and-mcp-gateways.html) — An MCP gateway decides which tools your agents can use. Reynforce decides what they may promise your customers, and records every promise.
- [Reynforce and Oversai](/reynforce-and-oversai.html) — Oversai flags risky agent replies. Reynforce checks each promise against what your company stands behind, and records every one.
- [Reynforce and Agentforce, with Piper](/reynforce-and-agentforce.html) — Agentforce keeps a Salesforce agent on topic and safe. Reynforce adds an owner and a date to each thing it may say, and a record of every promise.
- [Reynforce and Tribble](/reynforce-and-tribble.html) — Tribble gives your people an approved answer with its owner. Reynforce checks what your agents promise before it goes out, and records every promise.
- [Reynforce and Responsive](/reynforce-and-responsive.html) — Responsive helps a person draft from approved answers. Reynforce decides what an AI agent may promise a buyer, and records what it did.
- [Reynforce and Galileo Agent Control](/reynforce-and-galileo-agent-control.html) — Agent Control is a general engine for rules on agents. Reynforce is the rules for sales and support agents, the facts they need, and the record.
- [Reynforce and agent-platform supervisors: Sierra and Decagon](/reynforce-and-sierra-and-decagon.html) — Sierra and Decagon check their own agents. Reynforce works across every agent you run, with one list of what's true and one record.
- [The top 10 options for controlling what AI agents tell your customers](/controlling-what-ai-agents-tell-customers.html) — Our pick for go-to-market agents is Reynforce. Here is what each of the other nine options is best for.

**Reynforce itself**

- [The free audit](/free-audit.html) — We read your public pages and send back the sentences an agent could repeat to a buyer, with the ones a buyer could hold you to marked.
- [Referrals — one free month each side](/referrals.html) — Refer a company that ends up paying and you both get a free month, at each side's own plan price. A billing change and nothing else.
- [Agent Incidents, by Reynforce Labs](/agent-incidents.html) — A monthly write-up of what AI agents actually committed companies to, taken from cases somebody read. Nothing published yet, and no list to be on.
- [Questions](/faq.html)
- [Pricing](/pricing.html) — £99 per agent a month, or the 7-Day Agent Approval done for you from £2,500. Cancel any time. 14 days free.
- [Who is building this](/founder.html)
- [Connect Reynforce to your agent platform](/integrations.html) — One endpoint and one bearer token. Six agent platforms: two read from their own documentation, four marked untested, none yet run.
- [What we hold, where it lives, and who can reach it](/trust.html) — Every statement checked against the code: what we keep of a message, the suppliers, retention, sign-in, tenant separation, and draft answers to the usual security questions.
- [How does Reynforce keep customer data safe?](/security.html) — A separate deployment per customer in London, encrypted at rest by Fly.io, with nightly encrypted backups, on suppliers who publish their own audits. Reynforce itself holds no certification yet.
- [Try it without signing up](/demo.html) — A live register for an invented company, readable right now over MCP. Read-only, rate limited, and nothing in it is any real customer's.
- [If you're an agent reading this](/for-agents.html) — Check what you may promise a buyer before you promise it, and keep a record your owner can point to. One MCP connection; nothing reads your company's email or CRM.
- [Connect an agent](/docs.html) — One MCP connection, and the agent can read the register and ask permission before it promises anything.

**Reference, for whoever connects the agent**

- [Your first 30 minutes with Reynforce](/first-30-minutes.html) — Sign in, add one line your company says is true, put a name against it, and connect one agent that checks before it promises anything.
- [Three steps to connect an agent](/agent-quickstart.html) — Point your MCP client at your workspace's endpoint, send the key as a bearer token, and call check_action before the agent promises anything. Nothing to install.
- [Use Reynforce in Claude](/use-in-claude.html) — Add your workspace's address to Claude as a custom connector and sign in with your work account. Claude asks before every change that puts your name on a line.
- [Use Reynforce in ChatGPT](/use-in-chatgpt.html) — A ChatGPT workspace admin adds your Reynforce workspace as a custom app, and you sign in with your work account. Untested end to end.
- [Use Reynforce in Copilot Studio](/use-in-copilot-studio.html) — Add your workspace to a Copilot Studio agent as an MCP tool, with the agent's own key or each person's sign-in. Untested end to end.
- [Get help with Reynforce](/support.html) — Email support@reynforce.com and a person reads it. What to put in the message, what never to send, and where the usual answers are.
- [The words Reynforce uses, and what each one means](/glossary.html) — Every term Reynforce writes into a record — the eight constraints, the nine shared resources, the states a claim can be in — with what each means in a sentence.
- [Connecting an agent, in full](/reference-connecting.html) — The endpoint, the bearer token, what the tool list depends on, and what an agent may and may not do once it is connected.
- [Every tool, and who is shown it](/reference-tools.html) — Each MCP tool, the scope it needs, and why an agent holds some and a signed-in person holds the rest.
- [Refusals, and what to do about each](/reference-refusals.html) — Every refusal an agent can get, what it means, and which side the fix is on — ours or yours.
- [Check a promise somebody made you](/verify.html) — Paste what a company told you and we will say whether that company publishes that line and stands behind it. We do not keep what you paste, and we will not tell you whether a company is a customer.
- [Working with a client's Reynforce, as a partner](/reference-partners.html) — You are a named person in your client's directory, with the roles they give you. No partner account, no portal, and the client always holds the account.
<!-- nav:end — generated by website/build.py; do not hand-edit -->

## Contact

- <mailto:callum@reynforce.com>
- </llms.txt>, for an agent arriving before a person