Beyond the five core AI workers, configure bespoke workers for any domain-specific job your organisation needs done. No code. No deployment. Just configuration.
"We need an AI worker to review supplier contracts, flag risk, and route exceptions to legal."
Identity, models, tools, knowledge, review path, and escalation rules are configured before the worker starts work.
Generic AI platforms give you one-size-fits-all
Kaidera bespoke AI workers are configured for you
Configuring an AI worker means setting nine parameters. All nine are set through the platform configuration layer — the Lead worker handles this on your behalf when you describe what you need.
A natural-language identity that defines who the AI worker is, what domain it operates in, and what topics it must cover. The selected model uses this to guide every conversation — no hard-coded question flows needed.
"You are a Legal Contract Reviewer. Your role is to identify non-standard clauses, flag risk areas, and summarise obligations. Do not advise on jurisdiction-specific law."
Choose which AI capabilities power the worker and from which approved sources. Language models are only one category: workers can also use vision, voice, embedding, reasoning, code, or managed model programs depending on the business need.
frontier reasoning for contract analysis · efficient model for extraction · vision model for forms
Three-layer behavioral constraints: platform floor (inviolable), org floor (admin-set), and worker config. Lower layers can only add restrictions — never remove them. Guarantees AI workers cannot exceed their mandate.
"no_implementation_suggestions": true · "require_human_approval_on_write": true
Bind vetted platform capabilities to the worker. MCP-registered servers (registered via the MCP Server Registry) appear here alongside built-in platform capabilities. Each tool has a permission tier (READ / WRITE / EXECUTE / DESTRUCTIVE) and a minimum autonomy level. Workers can only use what they have been explicitly given.
web_search (READ) · write_database (WRITE, min autonomy 1) · deploy_staging (EXECUTE)
Five levels from fully human-controlled (0) to fully autonomous (4). Level 4 is reserved for internal Kaidera workers only — customers can configure workers up to level 3. Plan tier gates maximum autonomy.
Level 1: AI suggests, human confirms each action · Level 2: AI acts, human reviews results
Connect the worker to your organisation's external systems — BI tools, project trackers, databases, any REST API — through a unified 4-layer permission model. Credentials live in the approved secret store, never in the database.
Tableau (visualisation) · Jira (project tracking) · Snowflake (data warehouse) · Any REST API
An org-scoped vector store that grows with every session. The worker retrieves relevant prior interactions before responding — knowledge compounds. Data is strictly partitioned: one organisation's knowledge never leaks to another.
"Previously, this stakeholder mentioned the refresh cycle must be daily — reflecting that context now."
How users interact with the worker. Start with a web chat interface with topic-progress tracking. Extend to API invocation for programmatic use, or email mailbox for async stakeholder engagement.
Chat (web) · API (programmatic) · Email mailbox (async) — coming later
What happens when the worker completes its task. Route the output to a human reviewer by role (BA, architect, legal), set an SLA, and define what happens on approval or rejection. Powered by the human review integration system — see the dedicated deep dive.
On completion → assign to BA for review (SLA 24h) → on approve: export document → on reject: restart
You describe what you need. The Lead worker converts into the right accountable role — CPO for software development, CMO for marketing, or another lead role — and turns the request into a governed worker configuration. No code change. No deployment needed.
You describe the worker to the Lead
"I need an AI worker that gathers Tableau dashboard requirements from our data stakeholders"
The Lead creates the worker template
Sets identity, model capabilities, autonomy, and interface type
The Lead binds the tools
Approved search, document, workflow, and session tools are attached
The Lead configures steering
Behavioural constraints: no implementation suggestions, GDPR-compliant, require approval on write
The Lead connects external systems
Read-only dashboards, approved workflows, and relevant business systems are connected
Your worker is live
Immediately available in your workspace. Gets smarter with every session.
Any AI worker that needs domain expertise, organisation-specific constraints, and connections to your systems. These are just starting points.
Captures stakeholder requirements for any software or data project. Guides a structured conversation, generates EARS-formatted requirements documents, and routes for human BA sign-off.
Reads contracts, flags non-standard clauses, scores risk exposure, and produces a redline summary. Escalates to legal counsel for final sign-off before any contract is executed.
Connects to your Tableau workspace, understands existing dashboard structures, and gathers requirements for new visualisations. Proposes metric hierarchies based on your data model.
Reviews code changes and infrastructure configurations against your organisation's compliance policies. Flags violations, generates audit reports, and tracks remediation.
Don't start from scratch. Kaidera ships four pre-built Business Process Templates — fully configured AI workers ready to deploy into your organisation. All four have XML-structured steering enabled, delivering 15–30% fewer prompt tokens compared to Markdown format.
Extracts structured data from unstructured documents — invoices, contracts, forms. Routes extracted data for human validation before downstream processing.
Guides structured requirements conversations with stakeholders. Generates EARS-formatted requirements documents and routes to a BA for sign-off.
Connects to your data warehouse, interprets trends, and proposes predictive models. Presents findings with human-readable rationale before any model is deployed.
Receives, clarifies, and routes development requests. Decomposes work into actionable tickets, assigns estimates, and routes to the engineering team for prioritisation.
Platform templates are org-neutral — they appear in the template catalog for every organisation. Start from a template and it inherits your org's Steering Floor policies automatically. All four ship with XML-structured steering enabled.
Every session adds to the worker's knowledge store — an org-scoped vector database that is strictly private to your organisation. The more your team uses a custom worker, the better it becomes at understanding your organisation's specific context, terminology, and patterns.
Knowledge is strictly org-scoped. One organisation's data never influences another's workers.
Worker templates, tool catalog, autonomy levels, steering resolver, and human review system — all deployed and serving requests.
Visual Worker Builder Wizard, tool catalog browser, and human task queue UI — shipping soon.
Every custom AI worker can expose an A2A-compatible Agent Card endpoint for standardised discovery where that protocol is required.
Autonomy levels above Level 2 require Pro or Enterprise plans. Starter customers build workers with human approval at every step.
See also: Human Review Integrationand Billing
Custom AI workers are powerful. See how every token they use is metered, billed, and visible — with pre-paid credits, auto top-up, and hard-stop protection.
