Skip to main content

Documentation Index

Fetch the complete documentation index at: https://kasava.dev/docs/llms.txt

Use this file to discover all available pages before exploring further.

Kasava’s Agent isn’t just a chatbot — it’s an AI teammate that can take real actions across your codebase, project management tools, and product workflow. Ask it questions in plain English and get back rich, interactive results with real data.

​
What Makes It Different

Unlike generic AI assistants, Kasava’s Agent:
  • Knows your code — indexed repositories, symbol graphs, call chains, and framework patterns
  • Knows your product — customer signals, competitor landscape, OKRs, and plans
  • Connects to your tools — GitHub, Linear, Jira, Asana, Trello, Gong, and more
  • Takes action — creates issues, generates specs, exports plans, and schedules research
  • Shows, doesn’t just tell — returns interactive cards, charts, diagrams, and detail panels instead of walls of text

​
Capabilities at a Glance

Catch Me Up

Get up to speed on what happened while you were away

Sprint Insights

Recap sprints, track health, and spot velocity trends

Code Impact Analysis

Understand the blast radius before you change anything

Code Health

Monitor codebase quality and surface tech debt

Work Suggestions

Find the highest-impact thing to work on next

Feature Planning

Estimate difficulty and discover feature opportunities

Issue Management

Manage issues across GitHub, Linear, Jira, and Asana in one place

Customer Signals

Surface what customers are asking for and why

Competitor Intelligence

Track competitors and compare feature sets

Product Health

Get an executive-level view of your product’s status

Search

Find anything across code, docs, issues, and signals

Visualizations

See code flows, dependency graphs, and project structure

Plans & Documents

Generate PRDs, specs, and work breakdowns from a sentence

Prototypes

Generate ready-to-paste prompts for v0, Bolt, Lovable, and more

Bug Analysis

Analyze bug reports with code-aware root cause detection

Recurring Research

Schedule automated research that runs on a cadence

​
How It Works

The Agent runs as part of every chat conversation. When you ask a question, it decides which tools to use, gathers data from your connected sources, and returns results as interactive cards you can click into for more detail. Many results include detail panels — click a card to expand a right-side panel with full information, actions, and links back to your tools.
You don’t need to know the exact command. Just describe what you want in plain English. The Agent figures out which tools to use.