Weekly · by Pratima Chainani
Agentic AI, printed layer by layer. Shipped? Hyped? Skip-worthy?
What shipped in the agentic stack, what it means, and whether it held its colour. Misreads, fixed with extra tadka. Every claim dated and sourced. For devs and tech leads who skim.
Latest issues
All issuesISSUE 01
The first issue lands Wednesday 28 October.
Weekly, every WednesdaySubscribe and it comes straight to your inbox.
On the feed
@the.ajrak.ai
Reels
Faceless. Her voice. Never a repeat of a carousel.
Seven layers, one at a time
Every post is printed on one layer of the agentic stack. Over a month you see the whole pattern.
T7SDLC & teamsCoding agents, review, roles, delivery
T6Security & governanceOWASP agentic risks, EU AI Act, India DPDP
T5Evals & reliabilityEvals, tracing, quality in production
T4Orchestration & patternsWorkflows vs agents, harnesses, multi-agent
T3Tools & protocolsTool calling, MCP, A2A
T2Context & memoryContext engineering, retrieval, memory
T1Models & inferenceReasoning models, cost per task, routing
From the glossary
All termsT4 Orchestration
Agent harness
Everything around the model that turns it into an agent.
T4 OrchestrationWorkflow vs agent
Who decides the next step: your code, or the model.
T3 Tools & protocolsModel Context Protocol (MCP)
The open standard for how AI apps find and call tools and data.
T3 Tools & protocolsMCP vs A2A
Agent-to-tool vs agent-to-agent. Different layers, often used together.
T1 Models & inferenceTime horizon (METR)
How hard a task is at 50% success. Not how long the AI runs.
T5 Evals & reliabilityEvals vs benchmarks
Benchmarks rank models. Evals rank them on your work.