- Home
- Skills
- Agents & Orchestration
- ML Serving Architecture Selector
Works with the AI Agents you already use
ML Serving Architecture Selector
Choose and justify batch, real-time, streaming, edge, managed, Kubernetes, or serverless model serving with an evidence-tagged ADR.
$19
ML Serving Architecture Selector
Example session with this skill installed
We need to serve a 2GB LLM for internal document Q&A. We have 500 users, p99 latency needs to be under 2s, and our team has zero Kubernetes experience. Batch or real-time?
- Read your context and instructions
- Compiled the ml serving architecture
ARTIFACT: ML-SERVING-ADR
DECISION: Managed real-time endpoint; avoid self-hosted Kubernetes.
BINDING CONSTRAINTS
- [Verified] p99 latency under 2 seconds eliminates batch for the interactive path.
- [Verified] Zero Kubernetes experience eliminates self-hosted Kubernetes.
COST: requests/day × compute-seconds × current unit price; CALIBRATE request rate and vendor price.
STEELMAN: A 2GB model may create cold-start or memory constraints that require direct measurement.
REVISIT: Re-open the choice when measured concurrency, latency, cost, or team capacity crosses an approved threshold.
Connects securely to your tools. The creator never sees your data.
About this skill
Choose a serving pattern your team can actually operate
ML serving decisions are often made from technology preference instead of workload constraints. This skill turns latency, throughput, freshness, cost shape, team capacity, rollout needs, and compliance requirements into a structured architecture decision.
What it produces
- A binding-constraint register tagged Verified, Inferred, or Assumed
- An elimination pass for structurally unsuitable patterns
- A six-axis comparison matrix for the surviving options
- Cost formulas using supplied values and CALIBRATE markers where values are missing
- An ML-SERVING-ADR with the decision, strongest counterarguments, and revisit triggers
Patterns covered
Batch, real-time, streaming, edge, managed platforms, Kubernetes-based serving, and serverless inference. The skill compares architecture patterns; it does not deploy or configure any platform.
Best for
- Teams deciding whether online inference is actually necessary
- Architects comparing managed serving with self-operated infrastructure
- ML teams documenting why an option was eliminated
- Reviewers who need explicit trade-offs and conditions that reopen the decision
Boundaries
It does not query live prices, benchmark latency, provision infrastructure, prove compliance, or guarantee cost or performance. Provider-specific claims must be verified against current authoritative documentation.
Produces a decision artifact from supplied constraints; it does not deploy infrastructure, query live vendor pricing, benchmark latency, or guarantee cost or performance. Missing workload or team data is labeled Assumed or CALIBRATE. Runtime routing was not executed during package validation.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago
Permissions
No special permissions declared or detected