# Replicate Labs > Product documentation for Replicate Labs, the GTM harness. Reps bring live deals to an AI coach by voice or chat, practise against buyer personas built from those deals, and get scored against their own methodology. Managers see where the team is strong and where it is drifting. Every page below is available as Markdown at the URL shown. ## Getting started - [Documentation](https://replicatelabs.ai/docs/overview.md): How the coaching platform works, what your coach can do, and where to look when something is not behaving the way you expect. - [Signing in](https://replicatelabs.ai/docs/getting-started/signing-in.md): Sign-in methods, what a role actually controls, and why the screen you see may differ from a colleague's. - [Finding your way around](https://replicatelabs.ai/docs/getting-started/finding-your-way.md): The surfaces you will actually use: the coach home, the composer, the call, the Training Lab and configuration. - [Your first week](https://replicatelabs.ai/docs/getting-started/first-week.md): A day-by-day route from first sign-in to the point where reaching for the coach is a reflex rather than a task. ## Coaching - [How coaching works](https://replicatelabs.ai/docs/coaching/how-it-works.md): What the coach is reasoning from, why it interrogates your evidence, and the limits worth knowing before you rely on it. - [Bring a deal to a call](https://replicatelabs.ai/docs/coaching/bring-a-deal.md): The primary way to use the platform: open a call, talk the opportunity through, and leave with a next move and an agenda for next time. - [Working in chat](https://replicatelabs.ai/docs/coaching/chat.md): When typing beats talking, what to paste in, how long a source can be, and how to keep a thread useful. - [Getting a better answer](https://replicatelabs.ai/docs/coaching/asking-well.md): The difference between a generic reply and a useful one is nearly always the input. What to include, what to leave out, and how to push back. - [Coach buttons](https://replicatelabs.ai/docs/coaching/coach-buttons.md): The row above the composer: what each button does, why one might do nothing when clicked, and how the set is decided. - [What your coach remembers](https://replicatelabs.ai/docs/coaching/memory.md): How deal memory works, who else it reaches, and what to do when the coach is carrying something wrong. - [Skills](https://replicatelabs.ai/docs/coaching/skills.md): Repeatable jobs built into a coach so the output holds the same standard every time. What they are for, the one design constraint, and why one might not fire. ## Roleplay - [How roleplay works](https://replicatelabs.ai/docs/roleplay/overview.md): What a roleplay is made of, why the persona decides whether it is worth doing, and where it sits against live deal coaching. - [Running a roleplay](https://replicatelabs.ai/docs/roleplay/running-one.md): Getting into the Training Lab, what happens during the call, and the four mistakes that make a roleplay worthless. - [Personas](https://replicatelabs.ai/docs/roleplay/personas.md): What a persona is configured from, how those settings show up in the conversation, and what makes one worth practising against. - [Scorecards](https://replicatelabs.ai/docs/roleplay/scorecards.md): How a conversation is graded: items, levels, and feedback instructions, and why a scorecard edit resets your history. - [Reading your score](https://replicatelabs.ai/docs/roleplay/reading-your-score.md): What to take from a graded roleplay, what to ignore, and how to turn a weak criterion into an actual improvement. ## For managers - [The manager coach](https://replicatelabs.ai/docs/managers/manager-coach.md): A separate coach for people running a team: what to ask it, how it differs from the rep coach, and where it gets its answers. - [What you can see](https://replicatelabs.ai/docs/managers/what-you-can-see.md): Exactly what reaches a manager: the records you get in full, the coaching that reaches you as observations rather than a transcript, and how to answer a rep who asks. - [The coaching conversation](https://replicatelabs.ai/docs/managers/coaching-conversation.md): Using the platform to make your one to ones better rather than to replace them, and what to do with a rep who is not using it. - [Rolling out to a team](https://replicatelabs.ai/docs/managers/rollout.md): Getting a team from provisioned to genuinely using it, and the checkpoints that predict whether it will stick. ## Administration - [Users, teams and roles](https://replicatelabs.ai/docs/admin/users-teams-roles.md): The access model: how roles compose, what team membership changes, and how seats and offboarding work. - [What your coach knows](https://replicatelabs.ai/docs/admin/knowledge-base.md): Loading your organisation's material into the coach: scopes, accepted file types, size limits, and the formats that quietly fail to index. - [Building roleplays](https://replicatelabs.ai/docs/admin/roleplay-config.md): Composing a roleplay from a persona, a scorecard and a product, the order things must be built in, and how to make one feel like a real call. - [Building scorecards](https://replicatelabs.ai/docs/admin/scorecard-config.md): Writing items, levels and feedback instructions that grade consistently, and the two mistakes that make a scorecard useless. - [Coach configuration](https://replicatelabs.ai/docs/admin/coach-configuration.md): What is configured on a coach, which parts you change yourself and which go through your provider, and the change that most often breaks a live account. - [Planning a deployment](https://replicatelabs.ai/docs/admin/planning-a-deployment.md): The nine-box: one agreed planning grid that decides what gets configured, so the account is built from a plan rather than accumulated. ## Connect your tools - [Integrations](https://replicatelabs.ai/docs/integrations/overview.md): Connecting the tools your team already works in, what each one changes about the coaching, and how they are set up. - [ChatGPT and Claude](https://replicatelabs.ai/docs/integrations/chatgpt-and-claude.md): Connecting your coach to the assistant your reps already use, what it gives you, and where the platform is still the better place. ## Security and data - [Authentication and access](https://replicatelabs.ai/docs/security/access.md): Sign-in methods, the role model, single sign-on, and how access is scoped between organisations. - [Data, retention and deletion](https://replicatelabs.ai/docs/security/data.md): What is stored, who can reach it, how deletion works, and what to tell a security reviewer. ## Reference - [Glossary](https://replicatelabs.ai/docs/reference/glossary.md): Every term used across the platform and these docs, defined once. - [Troubleshooting](https://replicatelabs.ai/docs/reference/troubleshooting.md): The failures that produce no error message, in the order they actually happen, with the check that identifies each. - [Questions we get asked](https://replicatelabs.ai/docs/reference/faq.md): Direct answers on privacy, methodology, what the coach will and will not do, and the questions reps ask in week one.