Everything you need to build, with our estimates.
These are the pieces we had to build, grouped the way we built them. Effort is in engineer-weeks for a team that has done this kind of work before.
We built it as a loop that retrains itself.
Connect Loop from Fluint once. It captures every object, snapshots it over time, and studies the trajectory to model what wins, with ready-to-ship agents to do more of it. With every outcome flowing back in and retraining your private models.
A brief for every object, snapshotted through time.
Fluint builds a structured brief for every object in your GTM data. Each brief is a labeled summary of that object's dimensions, features, and the predictors attached to it: what the object was at a given moment, with the history of how it got there.
Every change writes a new timestamped state, so the model sees what changed and when. When a definition changes, history is backfilled and recompiled point-in-time, so no label leaks from the future.
Causal lift you can defend.
Because your data store is built in a time series structure, you're able to run a regression to attribute outcomes to their causal drivers, controlling for everything else moving in a deal. Each stage asks a different question, so we let you run a model suited to it, all deployed and monitored for you. Select a stage for examples:
Boosted trees rank behavior lift; a time-series model watches the deal's shape vs. healthy cohorts.
We provision the store and training jobs, retrain as deals close, watch every version for drift, and roll back when a release underperforms.
What we got wrong the first time.
Most of these looked fine in testing and only showed up once real deals ran through the models. If you build it yourself, plan for them from the start.
Stage and amount fields get overwritten as deals move. A model trained on current values learns from the ending, so it tests well and fails on open deals.
Won deals have more meetings because they were already going well. Treating meeting count as a predictor sent reps chasing the wrong thing.
RevOps renamed a stage mid-quarter. Old and new labels mixed in the training data and accuracy slipped for weeks before we caught it.
A pricing change shifted what wins in one segment. The model kept scoring the old pattern with full confidence.
Reps and managers read a coefficient table once. Nothing changed on their deals.
Assembling context when an agent asked for it was slow and burned tokens on every call.
How big is this for your team?
Move the inputs to match your setup. The ranges come from the spec above.
Assumes $220K a year per engineer, fully loaded. Upkeep covers retraining, drift checks, schema changes and new sources: about 1.2 engineers.
Three ways to get there.
Most teams we talk to want to own the projects their reps and leaders see, and would rather not own the pipeline underneath.
Your team owns every row of the spec, from ETL to serving.
We provision and maintain the store, models, drift checks and context. Your engineers build the agents and workflows on top.
Predictors, plays and proactive agents, ready for reps and leaders.
Build your projects on context that is already proven.
Everything in the spec above sits behind one MCP tool. Add Fluint to any agent framework and spend your engineering time on the projects themselves. It returns conclusions your agent can act on: predictors, active plays, and the evidence behind them, already computed. The same call works from Claude, ChatGPT, Copilot, or your own agent.
Post to Slack when an open deal is missing its top predictor, with the play attached.
Rank accounts by how closely they resemble your past wins, for planning season.
Flag committed deals that lack the predictors your won deals had at the same stage.
Give managers the one play each rep runs least, with deals to practice on.
Private weights, never shared.
Your models are org-scoped with private weights, trained on your data alone. Enterprise-ready from day one.
