https://ravishah.dev/writing/ Ravi Shah is an Executive Architect at IBM Consulting UK&I, based in London, specialising in agentic engineering for Financial Services. Ravi writes about agentic patterns, context engineering, token budgets and shift-left security, and publishes runnable open-source companions to that writing. en-gb Thu, 25 Jun 2026 11:06:42 GMT https://ravishah.dev/writing/a-deep-agent-anatomy/ https://ravishah.dev/writing/a-deep-agent-anatomy/ Thu, 25 Jun 2026 11:06:42 GMT The four components behind deep agents — a detailed system prompt, a planning tool, sub-agents and a file system — and how they differ from shallow ReAct agents. Ravi Shah agentic-engineering deep-agent artificial-intelligence agentic-ai ai-learning https://ravishah.dev/writing/token-budget-discipline/ https://ravishah.dev/writing/token-budget-discipline/ Tue, 26 May 2026 05:43:48 GMT A practical playbook for treating model quotas like engineering budgets: route requests, reserve premium capacity, and avoid cooldown stalls. Ravi Shah software-engineering generative-ai-tools llm-applications ai-economics token https://ravishah.dev/writing/ibm-project-bob-shift-left-security/ https://ravishah.dev/writing/ibm-project-bob-shift-left-security/ Tue, 19 May 2026 10:29:33 GMT How AI-powered Gitleaks scanning moves security from a pipeline gate into the developer's PR loop — shift-left security for the agentic era. Ravi Shah security ibm generative-ai-tools ideais project-bob https://ravishah.dev/writing/context-engineering-patterns-agentic-applications/ https://ravishah.dev/writing/context-engineering-patterns-agentic-applications/ Tue, 19 May 2026 10:23:16 GMT Architectural patterns for supplying and structuring context so production AI agents behave reliably at scale. Ravi Shah agentic-engineering generative-ai-solution software-engineering building-ai-applications ai-finops https://ravishah.dev/writing/eight-agentic-engineering-patterns/ https://ravishah.dev/writing/eight-agentic-engineering-patterns/ Mon, 18 May 2026 07:55:08 GMT A field guide to agentic patterns — why most enterprise teams default to only two, and what to adopt next. Ravi Shah generative-ai-solution agentic-ai enterprise-architecture design-patterns software-engineering https://ravishah.dev/writing/hallucination-is-in-your-architecture/ https://ravishah.dev/writing/hallucination-is-in-your-architecture/ Mon, 18 May 2026 07:43:25 GMT When generative AI fails in production, the root cause is often system design — not model choice. Ravi Shah context-engineering ai-reliability generative-ai enterprise-architecture agentic-ai https://ravishah.dev/writing/year-of-coding-with-gen-ai/ https://ravishah.dev/writing/year-of-coding-with-gen-ai/ Fri, 02 Jan 2026 12:08:55 GMT Lessons from a year of building with Cursor and Gen AI — what 1.4 billion+ tokens of real development work taught me about agentic workflows. Ravi Shah https://ravishah.dev/writing/antigravity-vs-cursor-multi-agent-coding/ https://ravishah.dev/writing/antigravity-vs-cursor-multi-agent-coding/ Sun, 23 Nov 2025 12:32:06 GMT Comparing Google's multi-agent Antigravity IDE with Cursor Agent Mode — transparency, coordination, and where multi-agent coding is heading. Ravi Shah https://ravishah.dev/writing/agentic-banking-model-context-protocol/ https://ravishah.dev/writing/agentic-banking-model-context-protocol/ Thu, 26 Jun 2025 13:08:50 GMT How agentic banking moves beyond low-balance alerts to self-solving — using MCP to connect agents securely to Financial Services systems. Ravi Shah https://ravishah.dev/writing/circuit-breaker-pattern/ https://ravishah.dev/writing/circuit-breaker-pattern/ Sun, 27 Nov 2022 21:33:45 GMT Applying the circuit breaker resilience pattern to deliver fault-tolerant digital experiences under failure. Ravi Shah