# Kam AI

> Kam AI is an AI research workspace for sports markets. It aggregates fragmented odds, news, injuries, schedules, stats, watchlists, saved ideas, and outcome reviews so non-technical stats and analytics users can ask plain-English questions with grounded context.

Important notes:

- Kam AI is research, education, monitoring, journaling, and review, not a transaction engine.
- Kam AI should not be described as a guaranteed outcomes product.
- The ideal user is analytical, non-technical, and trying to understand changing sports-market information without building a data stack.
- The public docs are the Kam AI help center and project manifesto. They teach users and AI agents how to use Kam AI well, especially through source review, signal explanation, freshness checks, saved ideas, and outcome review.
- Admin and manual-data routes are protected operational surfaces and are not public product documentation.
- Trust rule: do not make weak signals sound strong. Show uncertainty, missing data, stale inputs, freshness state, and source disagreement.
- Answer rule: start with the useful conclusion, then source context, caveats, and one next check.

## Public Docs

- [Documentation](https://kam-ai.com/docs): Help center and manifesto for Kam AI. Includes popular articles, topics, source research guidance, prompt examples, playbooks, reading answers, verification, and troubleshooting.
- [Homepage](https://kam-ai.com): Product overview covering source aggregation, normalized objects, signal detection, agent explanations, saved ideas, pricing, and early access.
- [Blog](https://kam-ai.com/blog): Essays on AI leverage, efficient sports research workflows, vertical integration, and responsible research.
- [Getting started](https://kam-ai.com/blog/getting-started): Introduction to AI leverage without AI autopilot.

## Manifesto

- Kam AI exists because fragmented sports-market data should become useful research context.
- The product should not be another static dashboard.
- The product should help users ask better questions, check assumptions, understand source changes, and save what they learned.
- The product should earn trust through sober language, visible caveats, freshness states, and clear next checks.
- The website is the public explanation of the company, product philosophy, user workflow, and trust posture.

## Help Center Flow

- Lead with the user's problem, not the internal system.
- Provide search, popular articles, popular topics, and direct answers.
- Keep help copy short, practical, and written at a simple reading level.
- Use articles for common user friction: asking good questions, reading answers, verifying freshness, handling stale data, saving ideas, and dealing with overconfident answers.
- Avoid developer-first framing on public docs unless the page is explicitly for developers.

## What Users Ask Kam AI

- Board scan: which watched markets changed materially, and which sources are stale or delayed.
- Source review: where a data point came from, when it last changed, and whether there are conflicts.
- Signal explanation: what changed, what the prior value was, why it matters, and what needs verification.
- Freshness check: whether the source is fresh, stale, delayed, or unavailable.
- Market journal: save a market idea with reason, source snapshot, expected movement, and next check.
- Outcome review: whether a saved reason held up, whether market movement supported it, and what lesson to save.

## Good Prompt Pattern

Ask with three parts:

1. Object, signal, source, or saved idea.
2. What changed or what needs explanation.
3. The exact research decision or next check.

Example prompts:

- "Scan today’s NBA board. Which watched markets changed materially, and which signals are stale or delayed?"
- "Explain this line_move signal. What source changed, what was the previous value, and what should I verify?"
- "Save this market idea with my reason: I am watching Knicks spread because injury timing may be overreacted to. What needs to be true by close?"
- "Review this closed idea. Did the reason hold up, did market movement support it, and what lesson should I save?"
- "I am not technical. Explain the source context behind this signal like a stats analyst, not a developer."

## Answer Standard

- Use plain, professional language that is easy to scan.
- Lead with the answer, but separate signal from action.
- State the data basis before giving interpretation.
- Name caveats such as stale sources, missing injury news, small samples, and source conflicts.
- Include the strongest counterargument when the signal is thin.
- Keep final decisions human-controlled. Kam AI supports research and verification.
- Avoid filler, hype, and long explanations that do not change the user's next move.

## How Users Should Read Answers

- Summary: the short read. Treat it as a research note, not a command.
- Source: where the answer is grounded and which data changed.
- Caveat: what can break the thesis.
- Missing data: what Kam does not know yet or what may be stale.
- Next check: what to verify before making a decision.

## Verification Checklist

- Check whether the source is fresh, stale, delayed, or unavailable.
- Recheck injuries, starters, scratches, weather, schedule changes, and late news.
- Ask what missing data would change the answer.
- Look for repeated assumptions across saved ideas.
- Do not treat last-known data as current truth.
- Keep research confidence separate from guaranteed outcomes.

## Common Mistakes

- Asking only for an answer instead of asking for source, signal, caveat, and next check.
- Ignoring stale data.
- Overvaluing the last few games without checking role, matchup, and sample size.
- Skipping the counterargument.
- Stacking assumptions that depend on the same source or game script.

## Product Areas

- [Product thesis](https://kam-ai.com/#product): Why Kam AI focuses on research leverage rather than dashboard automation.
- [Workflow](https://kam-ai.com/#workflow): How users move from raw context to normalized signals and better follow-up questions.
- [Pricing](https://kam-ai.com/#pricing): Available plans for AI-assisted research and workflow access.
- [Early access](https://kam-ai.com/#footer-cta-title): Contact and signup entry point.

## Blog Posts

- [AI Leverage, Not AI Autopilot](https://kam-ai.com/blog/getting-started): Practical guide to using Kam AI while keeping decisions human.
- [The Efficiency-First Research Workflow](https://kam-ai.com/blog/advanced-strategies): How serious sports research changes when workflow drag is reduced.
- [Vertical Integration Is the Product Moat](https://kam-ai.com/blog/understanding-odds): Why ingestion, freshness, signal detection, prompt design, evals, admin review, and chat UX are connected.

## Technical Notes

- [Sitemap](https://kam-ai.com/sitemap.xml): Indexable public routes.
- [Robots](https://kam-ai.com/robots.txt): Crawler policy.

## Optional

- [Login](https://kam-ai.com/login): Authentication entry for protected user and operator surfaces.