Learning
How Hyperstruck turns finished work into reusable lessons that make every future run better.
In short
A learning is a lesson Hyperstruck has drawn from real work and proven over time, so your agents get better at the tasks they do repeatedly instead of starting fresh on every run.
Most agents handle the past in one of two broken ways. They forget everything between tasks and start every run from a blank prompt, or they remember everything indiscriminately and drown in their own history. Both fail for the same reason: the agent cannot tell which of its past experience should change what it does next.
Hyperstruck's learning system exists to make that judgement. It watches work finish, keeps the few lessons worth carrying forward, and brings them back automatically the next time they are relevant, so quality compounds run after run.
The learning system
Learning is automatic. It is not a mode you opt into or a quality you have to tune. When Hyperstruck runs the reasoning itself, a lesson drawn early in a task can improve the rest of that same task; when it sits underneath another framework purely as a learning layer, each finished run makes the next one better. Either way, you do not have to manage it.
Not everything an agent does becomes a learning, and that is the point. Hyperstruck keeps only lessons that are grounded in what actually happened, that could help in a different situation rather than just restating this one, and that are free of secrets or personal data. When a new lesson matches one already on file, it strengthens that lesson instead of adding a near-duplicate. The result is a small, trustworthy body of knowledge rather than a growing pile of noise.
What a learning is
A learning is a short, conditional rule: when this kind of situation comes up, do (or avoid) this.
When a customer signals they might switch providers, raise a retention offer before responding.
When an application is missing a required document, request it before declining the application.
When one person has dominated a meeting, invite the quieter participants in before it ends.
When a refund has already been issued, do not issue it a second time.
When an appointment is cancelled at short notice, offer the slot to someone on the waitlist before leaving it empty.
That is the whole shape of it, whatever the work: a specific, legible lesson an agent can act on, not a document to read or a log to search.
What makes it more than a note is that it earns its place. A rule that keeps proving useful is applied more readily; one that starts misleading is pulled back; one that nothing reconfirms fades over time. A rule builds authority by working across many separate runs, so a single lucky or unlucky outcome never decides its fate. And a learning only surfaces when it genuinely fits the task in front of the agent, not merely because it shares a topic, so your agent is never nudged by lessons that look related but are not.
What learnings are
Taken together, the lessons an agent accumulates behave less like a filing cabinet and more like judgement that sharpens with experience.
Weighed, not filed
Learnings are not sorted into rigid categories. The same lesson can act as a firm guardrail in one task and a gentle hint in another, depending on how well it has proven out and how relevant it is right now.
They mature
A lesson that has repeatedly proven itself becomes part of how the agent works by default, so it no longer needs spelling out. If it starts to fail, it loses that standing just as readily.
Shared only when safe
Lessons start private to a single agent. They are shared across a team only when they are genuinely general, well proven, and free of anything specific or sensitive.
Open to correction
New evidence can update or qualify a lesson instead of being ignored. A rule that works everywhere except one situation records that exception, so it keeps helping where it fits and stays quiet where it does not.
Hyperstruck can also ship with a curated starter set of lessons, so a brand-new deployment is not starting completely cold. As an agent builds up its own experience, that starter knowledge naturally gives way to lessons earned on your actual work.
What they are not
The sharpest way to understand a learning is by what it deliberately is not.
- Not a memory of past conversations. Hyperstruck does not replay transcripts or treat run logs as knowledge. A learning is a distilled, reusable rule, not a recording of what was said or done.
- Not document retrieval. A learning is not a passage pulled up because its words resemble your goal. It surfaces because it genuinely fits the situation, not because it shares keywords.
- Not a one-run impression. Something an agent sees once, even several times within a single task, is not yet a learning. Knowledge has to prove out across separate runs before it is trusted, which stops an agent from convincing itself of a pattern it really only saw once.
- Not a fixed label. Nothing decided up front locks a lesson in as a warning or a tip forever. Its weight is judged in context, every time it comes up.
- Not a hunch that hardens on sight. A lesson seen once is a suggestion to weigh, never a rule to obey. It earns authority by proving useful, not by being repeated.
- Not permanent truth. A lesson loses standing when nothing reconfirms it, when later evidence contradicts it, or when it leads the agent astray. Letting the wrong lessons fade is part of the design, not a flaw in it.
- Not a place secrets live. Credentials and personal data are stripped out before anything is stored, and lessons that touch sensitive ground are never shared between agents.
Where this fits
Reasoning is how Hyperstruck makes good decisions in the moment. Learning is how it makes better decisions next time. To work with lessons directly, to store, search, retrieve, and reinforce them, see the Learnings API. To see how lessons shape a live run, see Reasoning.