> ## Documentation Index > Fetch the complete documentation index at: https://docs.unpod.ai/llms.txt > Use this file to discover all available pages before exploring further. # Intelligence > Definable intelligence blocks that turn conversations into structure - and the per-org model your communication state trains. Intelligence is **definable blocks**: a block takes communication in and writes structure out - extraction, qualification & scoring, summarization, sentiment & intent, evaluation, or a custom block you define. Today blocks run on call outcomes; where the system is headed is placement anywhere in the pipeline - attached to a single step, a conversation, or the whole stream (in build). Every insight lands back in communication state, where the next block - and the next agent - can read it. That loop is the point. Because outcomes accumulate in one durable system of record, the memory can become a model: outcomes feed a dataset builder, the dataset drives RL simulation, and the result is a per-org SLM (\~1B) served at your inference endpoint. You keep the trained model. A competitor arriving later starts at zero on the one input that cannot be bought, scraped, or copied: your own conversation history. ## The primitives | Primitive | What it is | Where it lives today | | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- | | Blocks | A defined unit of analysis (extraction, scoring, summarization, sentiment & intent, evaluation, custom) attached to a step, a conversation, or the stream | Extraction, scoring, and summarization run on call outcomes - see [Post-call data](/api/post-call-data) | | Datasets | Outcome history from communication state, assembled by the dataset builder into training data | Early access, with SLM training | | Evaluations | Blocks that score whether a conversation did its job, per turn or per outcome | [SuperDialog evals](/superdialog/evals) is the callable surface today | | Trained models | The per-org SLM (\~1B) trained on your outcomes and served at your inference endpoint | Early access | ## On the spine Blocks read interactions, outcomes, and context; they never touch the audio path. What a block produces is written back to communication state - onto the [outcome](/core-engine/outcomes) it analyzed or into the [Context Graph](/core-engine/context-graph) - so downstream blocks and agents read it as ordinary state, not as a side channel. Each insight written emits an event, like any other change on the spine. ## What stays hidden The training pipeline internals: how the dataset builder samples and labels outcomes, the RL simulation environment, and the fine-tuning stack behind the per-org SLM. You define blocks, ratify evaluations, and call the inference endpoint; how the model gets from your outcomes to that endpoint is not a surface you configure. ## Status * Definable blocks: extraction, scoring, and summarization run on call outcomes in production today via [Post-call data](/api/post-call-data); placement on arbitrary steps and streams is in build. * Evaluations: conversation-level evals callable today through [SuperDialog evals](/superdialog/evals). * Per-org SLM training (datasets, RL simulation, trained models): early access. ## Go deeper The API where extraction, scoring, and summarization results land today. The structured records blocks read from and write back to. Where insights persist as retrievable communication memory. Score conversations against ratified expectations.