OBSERVE
A lightweight agent installs on the employee's machine with explicit opt-in permissions. It captures behavioural metadata — app sequences, action patterns, timing — without ever reading the content of messages, documents, or files.
Your company already knows how to work.
Now it can remember.
praxic watches how your team works, detects the patterns they can't see themselves, and turns those patterns into approved automations — so institutional knowledge stops living only in people's heads.
Request early access
Currently accepting design partners for teams of 20–200.
The problem
Your most critical workflows were never written down.
Every company runs on workflows that exist only in the habits of its people. The operations manager who exports the same report every Friday. The customer success rep who copies information between three tools after every call. The engineer who writes the same status update every sprint. These patterns are real, they recur constantly, and they are completely invisible to every documentation system, wiki, or AI tool you have tried.
The only way to find them is to watch how people actually work. Not what they say they do. Not what the wiki claims. What they do.
The shiftYou don't prompt praxic.
You don't prompt praxic.
praxic prompts you.
Every AI tool on the market waits for you to tell it what to do. You write the prompt. You define the task. You do the cognitive work of recognising what needs automating.
praxic inverts this entirely. Every action your team takes is a prompt. Every app opened, every sequence repeated, every workflow run — these are behavioural signals. praxic reads them continuously, finds the patterns, and surfaces the automation opportunity to the employee at exactly the right moment.
The prompt is the work itself. You just have to be watching.
Every repeated sequence → a promptEvery workflow run → a signalEvery pattern detected → a suggestion
How it works
Observe. Suggest. Run.
Three layers, one continuous loop — from passive observation to an autonomous skill that runs without anyone asking again.
SUGGEST
When a recurring workflow crosses a confidence threshold, praxic surfaces it to the employee at a natural break in their day. Plain language, estimated time savings, step-by-step breakdown. They approve, edit, or dismiss.
RUN
Approved automations run autonomously and join the company's shared skill library, compiled to the Anthropic Agent Skills open standard. Every skill is portable, auditable, and owned by the company.
The differenceDocument indexing finds what people wrote down.
Document indexing finds what people wrote down.
praxic captures what they never thought to write.
Every “company brain” product you have seen indexes your documents, drops them into a retrieval pipeline, and calls it institutional knowledge. That fails for a structural reason: the most valuable knowledge was never written down, and the documents that were are contradictory, outdated, and unmoderated.
praxic derives knowledge from behaviour, not text. From what people actually do, not what the wiki says they should do. That is a categorical difference in the quality of knowledge that comes out the other side.
“The most valuable operational knowledge in any company has never been in a document. It lives in the sequence of actions a person takes without thinking about it.”
Open standards
No lock-in. Open by design.
Every skill praxic creates is compiled to the Anthropic Agent Skills open standard — now supported by Atlassian, Notion, Figma, Zapier, and others. Integrations are handled through the Model Context Protocol (MCP), now under the Linux Foundation. Your skill library works across any compliant agent platform, not just ours.
Anthropic Agent SkillsModel Context Protocol (MCP)
Privacy by architecturePrivacy enforced at the architecture level.
Privacy enforced at the architecture level.
Not by policy.
No content fields in our data schema
We cannot capture what we have no field for. Message bodies, document contents, and sensitive fields are excluded at the schema level, not by policy after the fact.
All behavioural processing runs locally before any transmission
Raw signal stays on the device. Only anonymised, aggregated pattern metadata ever leaves the machine — and only with the employee's active knowledge.
Real-time transparency dashboard for every employee
Anyone can see exactly what behavioural metadata is stored about them, per app, per day. Deletion is one click. Managers see the skill library — never individual data.
Built by
A small team that has lived this problem.
Natasha Zaborski
Co-founder & CEO
Waterloo. AI Strategy Consulting at Microsoft, where she analysed Copilot's competitive position across the North American SMB market. Software Engineering intern at Muskoka Woods. Building AI products.
Krish Punjabi
Co-founder & CTO
Waterloo Software Engineering. Y Hacks winner. Software Engineer at Ciena. Building the observation agent and pattern recognition pipeline.
We're building praxic now.
If this resonates, get in touch.
We're looking for design partners — teams of 20–200 who want to build this from the beginning.