How a question becomes an answer
Ask a question and the coach doesn't reach into a pre-written script — it reaches for a tool. get_player_stats pulls career VPIP/PFR/AF/WTSD/fold-to-cbet/3-bet straight from the database, broken out by position. search_hands and get_hand pull the exact hands behind a claim. calculate_equity runs the real Monte Carlo engine instead of estimating a percentage from memory. run_cfr_solver and predict_value reach for the solver and the neural value net for spots that need more than a hand count. web_search is there too, but only for outside strategy context — it's never asked to substitute for your own numbers.
Local by default, cloud when it's worth it
Routine analysis — a hand review, a quick stat pull — runs through whichever provider is configured, with local Ollama models available as a no-key fallback so nothing is ever fully blocked on an API key. Provider choice is yours: Anthropic, OpenAI, Gemini, DeepSeek, or ASI:One, switchable without losing the coach's memory of you.
That memory is durable, not just conversational. Sessions carry forward per player profile, so a leak flagged last week doesn't need to be re-explained this week.
One database, three places, one source of truth
The desktop SQLite file is authoritative. Every hand it imports mirrors out to Cloudflare object storage as raw JSON and into a relational index for fast lookups by player or position — both updated the moment the hand lands, not on a nightly batch.
For anything that needs the live number, not a synced one, a bearer-token-gated tunnel connects straight to the desktop database itself, so a query run from your phone reads the same table your HUD is reading from right now.
Reachable anywhere Claude is
The whole surface is exposed as a standard MCP connector — no bespoke app, no separate login. Add it once in Claude's connector settings and the coach has the same database access whether you're at your desk mid-session or asking from the rail on your phone.
leaksnipe · coach sessionlive query
am I good to call here — 9s6h on Jd3hAs, facing a pot-sized bet?
calculate_equity hero=9s6h board=Jd3hAs villain_range=cbet-range…
22.4% equity against a standard c-bet range on this texture. You need about 33% to call profitably at pot odds this size — this isn't close, it's a fold.
what's my fold-to-cbet from the big blind?
querying player_position_facts…
57% — high. Standard from the BB specifically sits closer to 45%