Ashish Kumar

A four-part series · 234 min of reading

Agentic architecture patterns

A four-part reference on how agents are built: the loop inside one agent and the patterns at each of its seams, the topologies that join many agents and the ways they fail together, the control plane that decides whether any of them may run, and the harness engineering that builds the loops and graphs by hand.

Start here

Part 1 of 4
Infographic: the agent loop drawn as a ring of four seams, with tau2-bench retail reliability in the centre falling from 0.74 right once to 0.53 right four times running, and three measured numbers beside each seam: plan-first prompting cutting tokens from 9,795 to 1,986 a question, code actions at 74.4 percent against 52.4 for JSON, cached input at $0.30 against $3.00 per million, and airline reliability falling from 0.56 to 0.40; a strip below prices a worked refund agent at $0.159, $0.071 or $0.008 a task.
Part 1 of 4 · 14 October 2026

Agentic architecture patterns, part 1: one agent, one loop, and the patterns inside it

An agent is a loop with four seams: the model call, the tool call, the context window and the stop condition. Part 1 of four argues that every single-agent pattern, from ReAct to compaction to the step cap, is a decision at one of them, and gives the measured record for each: what the pattern buys, how it fails, and the pass^k numbers that show which decisions hold.

67 min readStart reading Part 1 →

Then read on

Parts 2 to 4, in order
  1. Part 2Infographic: a dot plot of the change in success from adding agents at equal compute across six benchmarks, ordered from work that splits to work where each decision depends on the last, from plus 80.8 percent on Finance-Agent to minus 70 percent on PlanCraft, coloured by architecture; beside it a table of turns, error amplification and success per thousand tokens for five architectures, and three key numbers: 97 percent merge interference recovered to 82 percent by one message, 84.7 percent of report errors starting at the orchestrator, and $2.05 against $0.33 for one agent versus a lead with five small workers.

    Agentic architecture patterns, part 2: many agents, and the ways they fail together

    Many agents are a partitioning decision, not a staffing one. Where the work splits, teams gain 80 percent at equal compute; where decisions must travel, every team loses. Eight patterns and their failure record, drawn.

    15 October 2026 · 62 min read
  2. Part 3Infographic: a matrix of sixteen agent incidents from May 2025 to October 2026 against eight controls, with a dot where the control was missing (identity and egress 8 each, injection 6, approval and observability 4, durability 3, stop 2, classification 1), beside paired bars showing a rule as a request against the same rule as a control: attack success 17% in the prompt versus 4% at runtime, 33.7% versus 0.8% with computed roles, 37.5 to 60% irreversible harm ungated versus 2.5% with an enforced gate, and 94% of leaders confident versus 32.7% enforcing least privilege.

    Agentic architecture patterns, part 3: the control plane, the patterns that decide whether an agent may run

    A control is something the agent cannot read. Nine patterns that sit outside every agent, with what each costs in milliseconds, the measurements, and the incident of 2025 or 2026 each would have caught.

    16 October 2026 · 56 min read
  3. Part 4Infographic of the Nightly harness as a graph around a loop: a 2 a.m. routine and a workflow script running 8 upgrades at once feed a Stop-hooked loop capped at 30 turns and $2 a pass, then a test gate, a durable approval interrupt and a pull request as the only write, with a $80 worst night. Below, a log ruler of the caps platforms ship, from 3 sub-agent levels and 8 Stop-hook blocks to 1,000 agents per workflow run and 4,096 items per parallel call, with the three settings that default to no limit.

    Agentic architecture patterns, part 4: harness engineering, hands-on, with the loops and graphs that run the model

    The harness is now the product. A hands-on guide to loop engineering and graph engineering: what stops a loop, what a graph saves, and a complete harness built piece by piece with the numbers that bound it.

    17 October 2026 · 49 min read