← Back to the catalog

Team · Version 1.0.0

AI automation and cost control

Team members: 9

Choose suitable APIs, bound spending and build measurable, recoverable AI workflows.

Why add it?

Details… Show less

AI automation and cost control

Choose suitable APIs, bound spending and build measurable, recoverable AI workflows.

Members: Alina, Cato, Ellis, Freya, Nia, Noel, Oswin, Selene, and Zora. Includes their complete profiles, portraits and 48 shared supporting skills.

Install the team, then assign it to a project. The shared specialists and their skill dependencies travel together.

What is included

Agents 9

Teams 1

AI automation and cost control

Skills in this team 48

Explore the skills assigned to this team. Open a card for a clear explanation, a practical example and the agents who use it.

AI model and provider selection

Compares AI candidates on your real tasks, acceptable errors, operating constraints and cost per usable result.

ai-solution-benchmark-selection

Included files 1

SKILL.md

LLM evaluation and observability

Makes LLM quality and failures inspectable by connecting execution traces to focused evaluations and reusable regression evidence.

llm-eval-observability

Included files 1

SKILL.md

LLM provider adapters

Provides a consistent application-facing contract across LLM APIs while retaining the provider details needed for correct replay and accounting.

llm-provider-adapters

Included files 1

SKILL.md

Compare engineering options

Helps choose between realistic solutions by considering development effort, ongoing maintenance and the consequences of changing course later.

trade-off-lifecycle-cost-analysis

Included files 1

SKILL.md

Discover product data flows

Traces actual product, commercial and personal-data workflows before legal analysis or document drafting.

product-data-flow-discovery

Included files 1

SKILL.md

Isolated prototypes and benchmarks

Tests a risky technical assumption in a small controlled experiment before committing to an implementation approach.

empirical-micro-benchmark-prototyping

Included files 1

SKILL.md

Grade technical research evidence

Labels capability claims according to documentation, inspected source, executed experiments or explicit inference.

evidence-grading-research-verification

Included files 1

SKILL.md

AI spending admission controls

Reserves budget before billable AI work starts and reconciles usage without hiding unresolved provider charges.

ai-budget-admission-control

Included files 1

SKILL.md

Financial and quota invariants

Checks balance conservation, reservation limits and replay safety across generated financial and quota operations.

financial-quota-properties

Included files 1

SKILL.md

Debug concurrent data changes

Finds why concurrent requests lose updates, create duplicates or violate business invariants.

data-concurrency-debugging

Included files 2

LICENSE.txt
SKILL.md

Token and cache accounting

Turns differing provider usage reports into comparable records while preserving cache, reasoning and incomplete-stream distinctions.

llm-token-cache-accounting

Included files 1

SKILL.md

Versioned pricing calculations

Calculates costs against immutable effective-dated rates while keeping internal cost separate from customer charges.

versioned-pricing-cost-calculation

Included files 1

SKILL.md

Concurrent correctness properties

Tests whether concurrent operations preserve business invariants across controlled scheduling orders, with reproducible counterexamples when they fail.

concurrency-properties

Included files 1

SKILL.md

Durable agent execution

Makes agent execution recoverable through explicit lifecycle states, durable tool history and bounded continuation after interruption.

agent-runtime-state

Included files 1

SKILL.md

AI usage reconciliation

Reconstructs AI charges from provider usage, pricing versions and internal records while keeping unexplained differences visible.

ai-provider-usage-reconciliation

Included files 1

SKILL.md

Verify usage metering

Tests usage accounting for conservation, precise accumulation, duplicate delivery and historical pricing consistency.

metering-verification

Included files 1

SKILL.md

Deduplicate accounting events

Keeps repeated usage events from creating duplicate charges while retaining a reconstructable accounting history.

deduplication-accounting-integrity

Included files 1

SKILL.md

Cost attribution and reconciliation

Connects individual resource charges to owners and execution records, then compares internal totals with provider reports.

cost-attribution-reconciliation

Included files 1

SKILL.md

Cost reports with drill-down

Builds understandable cost reports whose totals lead to the underlying tasks, runs and immutable usage records.

cost-reporting-drill-down

Included files 1

SKILL.md

Tenant-aware retrieval evidence

Builds retrieval that can justify answers with authorized, versioned evidence and acknowledge when available sources do not support a claim.

tenant-rag-evidence-quality

Included files 1

SKILL.md

Tenant isolation verification

Tests tenant boundaries adversarially using comparable data in two workspaces, including indirect relationships and shared infrastructure.

tenant-isolation-verification

Included files 1

SKILL.md

Agent memory and retrieval

Organizes reusable agent knowledge with source history, scope and freshness controls, then retrieves evidence suited to the current task.

agent-memory-retrieval

Included files 1

SKILL.md

Tenant-safe caches, search and files

Extends tenant isolation beyond database rows to caches, search suggestions, derived indexes and stored file access.

tenant-aware-cache-search-files

Included files 1

SKILL.md

AI context engineering

Organizes AI session context into stable instructions, verified history and current work so compaction preserves actionable state.

context-engineering

Included files 1

SKILL.md

Agent trust boundaries

Places deterministic controls around agent tools so untrusted documents cannot freely turn access to sensitive data into external actions.

agent-permissions-trust

Included files 1

SKILL.md

Recoverable AI automation

Separates replayable workflow state from model calls and external actions so interrupted automation can resume safely.

durable-ai-automation

Included files 1

SKILL.md

Track workflow execution

Makes workflow progress traceable through runs, steps and attempts without showing unverified success.

execution-tracking-verification

Included files 1

SKILL.md

Workflow state modeling

Separates workflow meaning, canvas layout and execution history into explicit versioned models and state transitions.

workflow-semantics-state-modeling

Included files 1

SKILL.md

Durable waits and events

Makes workflows waiting for deadlines or external events survive restarts and duplicate wake-up signals.

durable-waits-event-correlation

Included files 1

SKILL.md

Retries and compensation

Recovers failed workflow steps using durable results, bounded retries and explicit handling of uncertain external effects.

retries-compensation

Included files 1

SKILL.md

Human approval steps

Adds durable human decision points to workflows with exact request binding, decision permissions and clear expiry behavior.

approval-human-tasks

Included files 1

SKILL.md

AI workflow step integration

Embeds AI steps in workflows with validated outputs, durable checkpoints, scoped tools and evidence of external effects.

ai-tool-step-integration

Included files 1

SKILL.md

AI evaluation and release criteria

Evaluates AI changes against representative tasks, explicit failure severity and reproducible quality, cost and latency criteria.

ai-evaluation-release-gates

Included files 1

SKILL.md

Validating property tests

Checks the credibility of property tests by validating independent expectations, meaningful generated cases and sensitivity to known faults.

test-oracle-generator-validation

Included files 1

SKILL.md

Risk-based test planning

Allocates test effort according to the impact and likelihood of what a change could break.

risk-based-testing

Included files 2

LICENSE.txt
SKILL.md

Analyze performance measurements

Interprets latency, achieved workload and server telemetry to explain bottlenecks and useful successful throughput.

performance-measurement-analysis

Included files 1

SKILL.md

Deployment verification and recovery

Verifies a release in its actual runtime and selects a recovery path that accounts for data and schema effects.

deployment-verification-recovery

Included files 1

SKILL.md

Secure MCP tool contracts

Defines narrow model-accessible tools whose permissions are enforced by application code rather than tool descriptions.

mcp-tool-security-contracts

Included files 1

SKILL.md

Tool-calling contracts

Defines unambiguous AI tools with constrained inputs, validated execution and outputs that preserve useful context.

tool-calling-contracts

Included files 1

SKILL.md

Agent authorization

Restricts agent actions to both the delegating person’s authority and the agent’s assigned purpose, including paused and resumed work.

agent-authorization

Included files 1

SKILL.md

Check who can access what

Checks that people can only view and change what they are allowed to, including bulk actions and data exports.

authorization-verification

Included files 1

SKILL.md

MCP and CLI integration

Connects agent capabilities through typed tools, resources and subprocesses with strict transport and lifecycle handling.

mcp-cli-integration

Included files 1

SKILL.md

Protocol specification analysis

Translates protocol requirements into an integration contract and checks where reference implementations or libraries differ from the specification.

protocol-spec-reference-analysis

Included files 1

SKILL.md

AI context and cache efficiency

Reduces unnecessary context and cache costs while preserving task constraints, source evidence and access boundaries.

ai-context-cache-efficiency

Included files 1

SKILL.md

Structured AI output and streaming

Turns model responses into validated application data while treating incomplete streaming fragments as provisional.

structured-outputs-streaming

Included files 1

SKILL.md

AI tracing and recovery

Reconstructs failed agent runs from durable evidence and chooses recovery without duplicating uncertain external work.

ai-trace-failure-recovery

Included files 1

SKILL.md

Operational observability

Connects logs, metrics and traces to concrete questions about failures, performance and user impact.

observability

Included files 2

LICENSE.txt
SKILL.md

Bug evidence intake

Organizes incoming bug evidence into reported claims, observations and testable hypotheses before asking for missing context.

bug-intake-evidence-analysis

Included files 1

SKILL.md

Requirements

Orqestria installed on your computer.
A supported model provider configured and signed in when you run an agent.

Not checked in your app Install in Orqestria

The app shows what is already present and asks you to review the missing items before installation.

Download bundle

Get Orqestria

Download the app, then return to this exact version using the continuation link. You can also open the downloaded bundle in the app.

Download Orqestria for Mac

Continuation link

Continuation link Exact install link

Version 1.0.0+fa7280edc0e6255f617378e1

Installation creates a local copy. Review all files and prerequisites in the app. Imported skills are untrusted; installing never runs their scripts.