Learning Session:
From Ad Hoc Work to Deterministic Code
Buffaly takes on a task it could not predict beforehand, works through it in context, learns a reusable skill from that ad hoc success, and then converts the method into a code-based skill that runs deterministically. That progression is what turns exploration into dependable execution.
One business question, four stages of internalization
Every stage still answers the same operational question. What changes is how much of the method Buffaly has retained, structured, and made reusable.
How many patients are ready to be imported for a target office based on the relevant eligibility score logic?
Buffaly turns one-off success into repeatable execution
The important transition is not simply from expensive to inexpensive. It is from a task that had to be figured out on the fly to a capability that can be run again as explicit code.
Learning Progression
FOUR FULL STAGES1. Ad hoc task solved in context
Buffaly answered the question by working through the real task in context instead of relying on a predefined function.
- Buffaly started with the plain-language business question rather than a predefined function.
- It explored the real data path, inspected the relevant JSON score structure, and found the actual scoring fields that mattered.
- It moved from the initial exploration path to the canonical target and returned the working answer.
- This stage proves Buffaly can reason through an unfamiliar operational question in context.
FairPath Demos 3-30
2. Reusable skill captured
The successful ad hoc method was retained as a reusable skill so Buffaly no longer had to rediscover the workflow from scratch.
- The ad hoc workflow was turned into a reusable skill.
- A fresh session could ask the same question and reuse the learned method instead of rediscovering it.
- This demonstrates that Buffaly can retain the task in an agent-native form, not just answer it once.
ToGetFairPathPatientImportEligibilityGte3CountsByOrganizationSkill
3. Learned skill refined with better context
Once the reusable skill existed, Buffaly could tighten the workflow, add better guidance, and cut away wasted work.
- The learned workflow was refined with more concrete guidance and better target information.
- Buffaly corrected the query shape issue that surfaced during refinement and reran the workflow cleanly.
- This stage shows that reusable behavior can be tuned for efficiency before it becomes code.
ORDER BY with UNION correction during refinement
4. The method became a code-based skill
The learned method stopped being just remembered behavior and became explicit code that Buffaly could execute deterministically.
ToGetFairPathPatientImportEligibilityGte3CountsByOrganizationDeterministic __TOTAL__
- The learned task was turned into a deterministic ProtoScript-backed action.
- The code path computes thresholded counts directly and emits reusable results, including
__TOTAL__. - This is how the workflow becomes deterministic: a once-ad-hoc method is turned into a reusable code-based skill.
ToGetFairPathPatientImportEligibilityGte3CountsByOrganizationDeterministic - Session 3-30-5
HIPAA-safe output without flattening records into unstructured AI text
The learning curve above is the main story. Paired with it is a separate trust demonstration: Buffaly can operate over native patient data and emit only the allowed fields for administrative export instead of flattening protected records into unstructured AI text. That means learning speed and data safety can be shown together without mixing the two stories.
The first win does not stay trapped in one session. Buffaly retains the method so the task can be reused instead of rediscovered.
Once the method is understood, Buffaly can tighten it, structure it, and prepare it to become code rather than leaving it as loose workflow memory.
When the workflow becomes a code-based skill, the task is no longer an ad hoc guess. It becomes a reusable deterministic capability.
Working concept page built from recovered FairPath demo sessions and redacted for presentation use.