Chrysent Deep Research
Private betaLong-horizon research workflows are available in private beta. Outputs require human review.Long-horizon research workflows that combine web, code, and enterprise context — with citations to the underlying source and configurable depth.
The problem this solves
Some questions are too broad, technical, or open-ended for a single prompt. Today you paste context manually, run multiple searches, and assemble a report by hand.
You need a research workflow that combines web sources, your code, and your enterprise context — with citations attached to every claim and configurable depth so the work stays bounded.
What changes when you adopt Deep Research
Configurable horizon and depth
Define orientation, depth, and parallelism per run. Large efforts split across coordinated subagents with bounded parallelism.
Citations stay attached
Every claim in the output references the source — web page, code file and line, local document, Axis result, or MCP-backed system response.
Multi-source synthesis
Combines web research, codebase analysis, Axis Code, and Axis Knowledge Base into one coherent report.
How Deep Research operates
- 01
Define orientation, horizon, and depth
Choose how broad and how deep the run should go. Set controlled parallelism for large efforts.
- 02
Execute sub-research in parallel
Subagents research web sources, code, and approved enterprise context in parallel within your configured limits.
- 03
Synthesize and cite
Findings are grouped, synthesized, and coherence-checked. Citations stay attached to the underlying source.
Component map
- Research plannerDefines orientation, horizon, depth, and parallelism.
- Sub-research agentsCoordinated subagents with bounded parallelism.
- Source integrationWeb, code, Axis Code, Axis Knowledge Base, MCP sources.
- Citation engineMaintains the link between each claim and its underlying source.
For the full platform architecture, see /platform.
Who uses it and how
Strategy / Research
Scenario: You need a structured long-horizon investigation with citations you can verify.
Gain: A research workflow with bounded parallelism and traceable citations.
Engineering leadership
Scenario: You want a technical investigation that crosses your codebase, docs, and the web.
Gain: Multi-source synthesis with citations attached to every claim.
See the product surface
Product screenshots and a short demo walkthrough are available to design partners under NDA. Request access below to receive the latest captures and a recorded session.
Request access →Supported systems
Chrysent Deep Research integrates with the providers and frameworks below. Each entry shows the current support status. Documentation for the full integration list is coming soon.
- Web search providersGenerally available
- Axis CodeGenerally available
- Axis Knowledge BaseRoadmap
- MCP-backed sourcesTech Preview
Where it runs and how data is handled
Chrysent sells self-hosted software only. Software and retained product data remain in customer-owned or customer-controlled infrastructure. Customer-configured external model providers receive provider-bound request data under the customer's provider agreement. This model supports data sovereignty and residency requirements. Data handling and retention are described on the Data handling & deployment page. Security architecture, encryption, and incident response are documented on Security & trust.
Benchmark and evaluation methodology
The first public benchmark study is in preparation. Until it ships, design partners can request the evaluation methodology and a private run report under NDA via the contact form.
Other Chrysent products
Common questions
How is depth controlled?
Per-run configuration sets horizon, depth, and parallelism. Outputs are bounded accordingly.
How are citations preserved?
The research planner attaches a source reference to every claim. The final report links each citation back to its origin.