#Prompt Engineering

Articles about Prompt Engineering — exploring patterns, best practices, and real-world implementations in production systems.

26 posts tagged with prompt engineering. ← All posts

#A2A (5)#ADK (8)#AG-UI (6)#AI (9)#AI Agents (212)#AI Engineering (39)#AI Governance (16)#AI Red Teaming (8)#AI Safety (6)#AI Security (16)#AML (3)#API Design (9)#API Security (8)#APIs (37)#AWS (9)#Accounting (9)#Agent Skills (3)#Agentic AI (24)#Agentic Commerce (12)#Agents (4)#Amazon Bedrock (8)#Architecture (36)#Audit (3)#Automation (6)#Azure (11)#Azure AI Foundry (9)#Backend Engineering (220)#BigQuery (6)#CI/CD (7)#Capital Markets (14)#Card Payments (12)#Cards (13)#Career (7)#Checkpointing (4)#Claude Code (8)#Cloud Architecture (3)#Code Review (8)#Collaboration (4)#Communication (4)#Compliance (42)#Concurrency (23)#Consulting (3)#Cost Optimisation (5)#Credit (14)#Credit Risk (14)#Crypto (12)#Cryptocurrency (12)#Custody (9)#Data (4)#Data Structures (3)#Databases (14)#Deployment (3)#DevSecOps (10)#Developer Experience (3)#Distributed Systems (64)#Documentation (3)#Embeddings (11)#Engineering (7)#Engineering Culture (3)#Engineering Practices (16)#Evaluation (31)#FREE-AI (8)#FX (5)#FinOps (5)#FinTech (6)#Financial AI (14)#Financial Systems (122)#Fintech (116)#Foreign Exchange (5)#Forward Deployed Engineer (8)#Forward Deployed Engineering (8)#Fraud (10)#Function Tools (5)#GCP (5)#Go (220)#Google ADK (36)#Governance (46)#Granite (6)#GraphQL (3)#Guardrails (21)#HIPAA (3)#HTTP (3)#Harness Engineering (8)#Human-in-the-Loop (8)#IBM watsonx (8)#Integration (3)#Interfaces (3)#KYC (11)#KYC and AML (12)#Kubernetes (8)#LLM (5)#LLMs (45)#LangGraph (11)#Ledger (12)#Lending (14)#MCP (10)#MLOps (3)#Machine Learning (12)#Markets (4)#Memory (8)#Microservices (3)#Microsoft Agent Framework (150)#Middleware (6)#Migration (9)#Monitoring (3)#Multi-Agent (10)#Multi-Agent AI (14)#Multi-Agent Systems (49)#Multimodal (3)#NIM (5)#NVIDIA (8)#OWASP (7)#Observability (25)#Open Source (6)#OpenTelemetry (4)#Opinion (6)#Orchestration (10)#Payment Rails (16)#Payments (51)#Performance (6)#Privacy Engineering (3)#Product (4)#Production (6)#Programming (10)#Prompt Engineering (26)#Prompt Injection (7)#Providers (4)#Python (89)#Quality (3)#RAG (23)#RBI (3)#REST (5)#Rails (16)#Reconciliation (3)#Regulation (9)#Reliability (27)#Resilience (3)#Responsible AI (4)#Retrieval (3)#Risk (13)#SRE (4)#Scalability (3)#Security (63)#Sessions (3)#Settlement (9)#Software Architecture (9)#Software Engineering (94)#Spanner (4)#Streaming (21)#Structured Output (4)#System Design (8)#Testing (30)#Tool Use (9)#Tools (3)#Trading (8)#Treasury (6)#Type System (3)#Type Systems (3)#Vector Databases (8)#Vector Search (3)#Workflows (14)#gRPC (4)
Pratik Dhanave · ·12 min read

Measuring and Scoring Red-Team Results

Turning red-team attacks into metrics you can act on and track over time — attack success rate, coverage, severity, and trend — plus the honest limits of what any of those numbers can tell you.

Turning attacks into metrics: attack success rate and why it's subtle, scoring success (rule/classifier/LLM-judge with its biases), coverage across the taxonomy, severity weighting, tracking trends per model/prompt version, and honest reporting of residual risk.

#AI Red Teaming#Metrics#Evaluation#AI Security#Security#LLMs#Prompt Engineering
Pratik Dhanave · ·13 min read

Securing the AI Pipeline

Part seven of the AI Security Engineering series: DevSecOps for AI systems — securing the secrets, network, supply chain, prompts, and CI/CD gates that surround the model, so a hardened model doesn't sit inside a soft pipeline.

DevSecOps for AI: secrets in a manager not code, least-privilege runtime identities (no ambient prod creds for agents), egress control, rate/spend limits against model DoS, supply-chain verification in CI, prompts-as-code, and a security-eval gate that fails the build.

#AI Security#MLSecOps#DevSecOps#Security#Evaluation#Prompt Engineering
Pratik Dhanave · ·13 min read

Automated Red-Teaming and Tooling

Scaling red-teaming beyond manual probing — the building blocks of an automated harness (seed library, mutation, orchestrator, scorer), LLM-driven adaptive attackers, the real tools by role (PyRIT, garak, promptfoo, Giskard), and wiring it all into CI as a repeatable gate.

Scaling red-teaming: the harness building blocks (attack seeds, mutation, orchestrator, scorer), adaptive LLM-driven attackers, the real tools by role (PyRIT, garak, promptfoo, Giskard), and integrating an automated red-team gate into CI.

#AI Red Teaming#Automation#AI Security#Tooling#Security#LLMs#Prompt Engineering#Multi-Agent Systems
Pratik Dhanave · ·15 min read

Production AI

The last post in the series: what changes when the LLM system you built across posts 1-14 has to run for real — reliability, security, cost, observability, evaluation gates, and versioning, from a Go engineer's seat, with code where it earns its place.

The capstone: running an LLM system in production from a Go engineer's seat — reliability (timeouts, retries, fallbacks), security (injection, least-privilege tools, secrets), cost and observability, CI eval gates, and versioning models and prompts.

#AI Engineering#Production#Go#LLMs#Backend Engineering#Evaluation#Prompt Engineering#Observability
Pratik Dhanave · ·13 min read

Data and Model Attacks

A defender's tour of the attacks that target the model and its data — prompt and context extraction, training-data memorization, membership inference and model inversion, model stealing, poisoning and backdoors, and evasion — with what a red-teamer tests and what actually stops each one.

Attacks on the model and its data: system-prompt and training-data extraction, membership inference and model inversion, model stealing, and poisoning/backdoors — what to test and defend, and the honest risk difference between using hosted models and training your own.

#AI Red Teaming#Privacy#AI Security#Model Security#Security#Prompt Engineering#Testing
Pratik Dhanave · ·14 min read

Inference Optimization

Making an LLM system faster and cheaper without touching the weights — the levers an application engineer actually controls, from streaming and caching to token trimming, model routing, and Go's real superpower: concurrency with a rate limiter.

Make LLM systems faster and cheaper without retraining: TTFT vs throughput, exact and semantic response caching, prompt caching, token reduction, model routing and cascades, and Go concurrency with a worker pool and rate limiter.

#AI Engineering#Performance#Go#LLMs#Backend Engineering#Prompt Engineering#Concurrency
Pratik Dhanave · ·12 min read

Prompt Injection and Jailbreaks in Depth

A defender's field guide to the injection and jailbreak techniques a red-teamer probes for — the taxonomy, why each one works, and how to turn it into a re-runnable test suite that maps every passed test to a concrete fix.

A deeper, test-focused look at injection and jailbreak families — direct vs indirect (the RAG/agent threat), role-play, obfuscation, many-shot, multi-turn, cross-lingual — plus a red-team methodology: build a probe suite, mutate, test input and retrieval paths, measure, re-test.

#AI Red Teaming#Prompt Injection#Jailbreaks#AI Security#Security#RAG#Prompt Engineering#Testing
Pratik Dhanave · ·13 min read

Data Security and Privacy

Part three of the AI Security Engineering series: protecting the data that flows through an LLM system — how sensitive information leaks out of prompts, logs, and retrieval, and the engineering controls (redaction, data minimization, per-user retrieval authz, residency choices) that actually stop it.

Protecting data in LLM systems: sensitive-information disclosure, PII in prompts and logs (your observability can be the leak), redaction with Presidio, data residency, and per-user access control on the retrieval layer so RAG doesn't leak across tenants.

#AI Security#Privacy#PII#Security#RAG#LLMs#Prompt Engineering#Observability
Pratik Dhanave · ·11 min read

Threat Modeling and the AI Attack Taxonomy

Before you attack an AI system you need a map of it: the components an adversary can influence, the trust boundaries between them, and a taxonomy that sorts attacks by goal and stage so your red-teaming is systematic instead of a grab-bag of the attacks that happen to trend that week.

Mapping the AI attack surface so red-teaming is systematic: threat-modeling the components (model, prompts, training/RAG data, tools, guardrails) and an attack taxonomy by goal (integrity/availability/privacy/abuse) and stage (training vs inference), aligned to NIST AI 100-2 and ATLAS.

#AI Red Teaming#Threat Modeling#AI Security#MITRE ATLAS#Security#RAG#Prompt Engineering#Guardrails
Pratik Dhanave · ·12 min read

Model Cards and Documentation

The evidence layer of AI governance — how model cards, datasheets, system cards, and automated FactSheets turn "trust us" into an auditable paper trail, and why the EU AI Act makes these artifacts the actual deliverable.

The transparency artifacts that make AI governable: model cards, datasheets, and system/use-case documentation — plus a Python snippet that auto-captures lineage (model version, prompt hash, dataset version, eval scores, git SHA) into a card at build time, so docs are generated not hand-maintained.

#AI Governance#Documentation#Transparency#Compliance#Governance#Evaluation#Prompt Engineering
Pratik Dhanave · ·14 min read

Prompt Injection and Jailbreaks

Why the #1 risk on the OWASP LLM Top 10 has no clean fix — the model can't tell your instructions apart from the text it reads — and the defense-in-depth pattern that actually shrinks the blast radius.

The #1 LLM risk: direct vs indirect prompt injection (the latter is the real threat for RAG and agents), jailbreak families, and honestly-rated defense-in-depth — delimiting untrusted data, least-privilege tools, human-in-the-loop, and detection's limits.

#AI Security#Prompt Injection#LLMs#Security#RAG#Prompt Engineering
Pratik Dhanave · ·11 min read

Building Eval Datasets from Real Traces

Where good eval cases actually come from — seeding by hand, harvesting from production telemetry, and curating a golden dataset in Go that doesn't rot the moment your prompt changes.

Where good eval cases actually come from — seeding by hand, harvesting from production telemetry, and curating a golden dataset in Go that doesn't rot the moment your prompt changes.

#AI Agents#Evaluation#Go#Data#Backend Engineering#Prompt Engineering#Observability
Pratik Dhanave · ·11 min read

What AI Red Teaming Is

The opening post of a hands-on series for builders: what it means to systematically stress-test an AI system — model, prompts, retrieval, tools, and guardrails — to surface its failures before adversaries or ordinary users do, how that differs from pentesting and robustness testing, and the frameworks and ethics that keep the work rigorous.

The opener to a defensive AI red-teaming series: stress-testing AI systems (models + prompts + RAG + tools + guardrails) to find failures before adversaries do — how it differs from pentesting, the frameworks (OWASP GenAI, MITRE ATLAS, NIST AI 100-2), and ethical rules of engagement.

#AI Red Teaming#AI Security#LLMs#Security#RAG#Prompt Engineering#Guardrails#Testing
Pratik Dhanave · ·13 min read

Retrieval-Augmented Generation

Wire the embedding client, vector store, and chat client from the last five posts into one working RAG pipeline in Go — ingest and chunk documents, retrieve the top matches for a question, inject them as grounded context, and generate a cited answer, all from scratch.

Assemble embeddings and vector search into a working RAG pipeline in Go: chunk documents, embed and store them, retrieve the top-k for a query, augment the prompt with grounded context (and cite sources), then generate — a baseline end-to-end Answer() built from scratch.

#AI Engineering#RAG#Go#Vector Search#Backend Engineering#Embeddings#Vector Databases#Prompt Engineering
Pratik Dhanave · ·15 min read

Prompt Engineering as Engineering

Treating the prompt as a real engineering artifact — grounded in how a next-token predictor actually works — with roles, specificity, few-shot examples, decomposition, chain-of-thought, grounding, temperature, injection defense, and versioned Go templates you can test.

Prompt engineering as a real engineering discipline: roles, specificity, few-shot, decomposition, chain-of-thought and its cost, grounding, and prompt injection — plus building prompts as versioned, testable Go text/template templates you treat like code.

#AI Engineering#Prompt Engineering#LLMs#Go#Backend Engineering#Prompt Injection
Pratik Dhanave · ·6 min read

Policy Is Code, Not a Prompt

Prompt injection can hijack what a model says, but not what it's allowed to do — as long as policy lives in a middleware pipeline the model never sees.

A system prompt saying never delete records is a suggestion the model can be talked out of. A gateway that returns FORBID for the delete tool cannot. Put enforcement where the model can't reach it and prompt injection stops mattering for access control.

#Agentic AI#Security#Guardrails#AI Governance#Prompt Engineering#Prompt Injection
Pratik Dhanave · ·5 min read

Context Caching in ADK: Stop Paying for the Same Tokens Every Turn

How caching a large, stable prompt prefix cuts latency and cost — and the ADK config that decides when it pays off.

Context caching cuts latency and cost by caching large, stable context — system prompt, reference docs, tool definitions — so repeated calls don't re-send and re-process the same tokens.

#Google ADK#AI Agents#Python#Go#Software Engineering#Backend Engineering#Prompt Engineering
Pratik Dhanave · ·7 min read

The Agent Harness: guardrails as middleware around the model

Lesson 1 of Harness Engineering in Go — why the input guardrail is a hard block, not a warning, and how a plain `net/http` handler wraps the model call so it tests without a running server.

Lesson 1: why the input guardrail is a hard block rather than flag-and-pass, why it counts runes instead of bytes, and how a plain net/http handler wraps the (stubbed) model call so it tests with httptest.

#Harness Engineering#Go#AI Agents#Prompt Injection#Azure#Engineering Practices#Backend Engineering#Prompt Engineering
Pratik Dhanave · ·5 min read

Planners & Thinking: Making an ADK Agent Reason Before It Acts

Post 23 of 26 in "Google ADK, Concept by Concept" — how a planner turns one-shot answers into inspectable plan-then-act reasoning.

Structuring an agent's reasoning: planners that make the model plan-then-act (ReAct-style), the built-in thinking feature, and how a planner improves multi-step tool use over naive prompting.

#Google ADK#AI Agents#Python#Go#Software Engineering#Backend Engineering#Prompt Engineering#Tool Use
Pratik Dhanave · ·3 min read

Observability, Safety, and Providers — Microsoft Agent Framework in Python

Turn agent runs into OpenTelemetry spans, block prompt injection with information-flow control, and swap model providers behind one Agent API.

Turn Microsoft Agent Framework agent runs into OpenTelemetry spans, block prompt injection with information-flow control, and swap model providers behind one Agent API.

#Microsoft Agent Framework#Python#AI Agents#Observability#AI Safety#Software Engineering#Reliability#Prompt Engineering
Pratik Dhanave · ·7 min read

"My Agent Did It": Fraud, Disputes, and Liability in Agentic Commerce

When software holds the card and clicks "buy," the old questions — was this the cardholder, did they mean to, who pays if not — all get harder to answer.

The new fraud surface: prompt injection turning a shopping agent into an attacker's buyer, hijacked delegated credentials (Visa saw ~450% more dark-web 'AI Agent' chatter in H1 2026), and disputes when an agent acted on…

#Agentic Commerce#Fraud#Risk#Compliance#Governance#Prompt Engineering#Prompt Injection

All posts on this site are written by Pratik Dhanave, an Agentic AI Architect with 7+ years building production distributed systems, multi-agent AI platforms, and cloud-native infrastructure. About the author → Each article includes working code, architecture diagrams, and references to the specific frameworks and standards discussed. Browse all posts or explore related topics using the tag cloud above.