Prompt
We track 19 posts about Prompt from 10 engineering blogs. Most active: Google Online Security, Vanilla Java, Vanilla Java. Latest post: Oct 21, 2026.
Companies writing about Prompt
Recent posts
Prompt Caching API Example: Cut Token Costs in Node.js (opens on the source site)
Structure stable prompt prefixes across OpenAI, Anthropic, and Gemini, then verify cache hits with each provider's usage metrics in Node.js. Continue reading Prompt Caching API Example: Cut Token Costs in Node.js on SitePoint.
PMania 6/6 - Du prompt au produit : votre premier workflow IA de bout en bout (opens on the source site)
Cinq épisodes pour comprendre l'IA, un seul pour l'assembler. Des retours bruts jusqu'au sprint validé, en passant par la synthèse, les user stories et les tickets : voici le workflow complet, avec deux points d'arrêt humains bien placés, pour de vrai, de bout en bout.
Prompt-Driven Development: Building with GitHub Copilot Coding Agents (opens on the source site)
We used GitHub Copilot coding agents to build an app across different time zones. The AI wrote the code, but prompts, tests, guardrails, and pull requests made it software development rather than vibe coding.
Your coding agent spends 26,000 tokens before it reads your prompt: Comparing MCP and CLI (opens on the source site)
PubNub: ·
AI adoption for coding has reached an all-time high, but there's a bottleneck nobody budgeted for. Explore what MCP servers, CLIs, and skill files actually cost you before an agent does any work, and a benchmarking measure using tooling from Blocks.ai (powered by PubNub).
Your next survey starts with a ChatGPT prompt (opens on the source site)
Ask AI what your customers think, and it will give you an answer. It just won't be their answer—it'll be a best guess, assembled from patterns, not from the people who actually use your product. That's the gap between working fast and working right. As more decisions get made inside AI conversations, the ones missing real human input are really just guesses with better formatting. Now you can close that gap without leaving the chat by connecting to the SurveyMonkey plugin within ChatGPT. Create surveys, publish them, and analyze responses—all in one continuous conversation that’s backed by…
Cypress cy.prompt Vs Recording Vs Coding (opens on the source site)
Cypress-the-company is putting a lot of effort behind its cy.prompt command (which I recreated in cypress-think), so let's see if it is any good. I took a simple login form and tried to create a test using three different approaches: coding in VSCode using "update the test / Cypress reruns it / update the test" using cy.prompt command from text recording user actions using Cypress Studio TLDR; only normal coding works reliably Coding by hand Here is the "normal" login test: we grab the username (not a secret) and password (secret) and enter them into the login form. cypress/e2e/spec.cy.js1 2…
AI threats in the wild: The current state of prompt injections on the web (opens on the source site)
Posted by Thomas Brunner, Yu-Han Liu, Moni PandeAt Google, our Threat Intelligence teams are dedicated to staying ahead of real-world adversarial activity, proactively monitoring emerging threats before they can impact users. Right now, Indirect Prompt Injection (IPI) is a top priority for the security community, anticipating it as a primary attack vector for adversaries to target and compromise AI agents. But while the danger of IPI is widely discussed, are threat actors actually exploiting this vector today – and if so, how?To answer these questions and to uncover real-world abuse, we…
AI threats in the wild: The current state of prompt injections on the web (opens on the source site)
Posted by Thomas Brunner, Yu-Han Liu, Moni Pande At Google, our Threat Intelligence teams are dedicated to staying ahead of real-world adversarial activity, proactively monitoring emerging threats before they can impact users. Right now, Indirect Prompt Injection (IPI) is a top priority for the security community, anticipating it as a primary attack vector for adversaries to target and compromise AI agents. But while the danger of IPI is widely discussed, are threat actors actually exploiting this vector today – and if so, how? To answer these questions and to uncover real-world abuse, we…
Mitigating prompt injection attacks with a layered defense strategy (opens on the source site)
Posted by Adam Gavish, Google GenAI Security TeamWith the rapid adoption of generative AI, a new wave of threats is emerging across the industry with the aim of manipulating the AI systems themselves. One such emerging attack vector is indirect prompt injections. Unlike direct prompt injections, where an attacker directly inputs malicious commands into a prompt, indirect prompt injections involve hidden malicious instructions within external data sources. These may include emails, documents, or calendar invites that instruct AI to exfiltrate user data or execute other rogue actions. As more…
Google Workspace’s continuous approach to mitigating indirect prompt injections (opens on the source site)
Posted by Adam Gavish, Google GenAI Security TeamIndirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the attacker to influence the behavior of an LLM by injecting malicious instructions into the data or tools used by the LLM as it completes the user’s query. This may even be possible without any input directly from the user.IPI is not the kind of technical problem you “solve” and move on. Sophisticated LLMs with increasing use of agentic automation combined…
Google Workspace’s continuous approach to mitigating indirect prompt injections (opens on the source site)
Posted by Adam Gavish, Google GenAI Security Team Indirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the attacker to influence the behavior of an LLM by injecting malicious instructions into the data or tools used by the LLM as it completes the user’s query. This may even be possible without any input directly from the user. IPI is not the kind of technical problem you “solve” and move on. Sophisticated LLMs with increasing use of agentic automation combined…
Improving the prompt to the AI to get better code (opens on the source site)
In a previous article I looked at one-shoting a solution to optimise code to show the variation in different AI. Thsi is the not the best way to get what you want however. More often you need to either refine the prompt or give feedback. After one-shoting the same prompt on multiple AI, I have created a refined prompt based on the various concerns with previous results. The prompt Based on the results in a previous run Asking multiple AI to optimise the same code Suggest how to implement this more optimally using low latency techniques to minimize any objects created. ## Use - a ThreadLocal…
Improving the prompt to the AI to get better code (opens on the source site)
In a previous article I looked at one-shoting a solution to optimise code to show the variation in different AI. Thsi is the not the best way to get what you want however. More often you need to either refine the prompt or give feedback. After one-shoting the same prompt on multiple AI, I have created a refined prompt based on the various concerns with previous results. The prompt Based on the results in a previous run Asking multiple AI to optimise the same code Suggest how to implement this more optimally using low latency techniques to minimize any objects created. ## Use - a ThreadLocal…
Mitigating prompt injection attacks with a layered defense strategy (opens on the source site)
Posted by Adam Gavish, Google GenAI Security Team With the rapid adoption of generative AI, a new wave of threats is emerging across the industry with the aim of manipulating the AI systems themselves. One such emerging attack vector is indirect prompt injections. Unlike direct prompt injections, where an attacker directly inputs malicious commands into a prompt, indirect prompt injections involve hidden malicious instructions within external data sources. These may include emails, documents, or calendar invites that instruct AI to exfiltrate user data or execute other rogue actions. As more…
Prompt Driven Development (opens on the source site)
Vibe coding (also vibecoding) is an AI-dependent programming technique where a person describes a problem in a few sentences as a prompt to a large language model (LLM) tuned for coding. The LLM generates software, shifting the programmer’s role from manual coding to guiding, testing, and refining the AI-generated source code. Vibe coding is claimed by its advocates to allow even amateur programmers to produce software without the extensive training and skills required for software engineering. The term was introduced by Andrej Karpathy in February 2025 and listed in the Merriam-Webster…
Prompt Engineering for AIDE (opens on the source site)
This article was AI-generated using this project as context. AIDE Project. The purpose of this project is to see how much an AI could generate given enough context, and in this project, all the "source" code is generated using the requirements and unit tests as context. This follows the Next-Level Development: Harnessing AI with AIDE approach. The main parts are: Requirements Documents in .adoc format. JUnit tests in Java. AIDE itself. AI-generated code in Java. Even the articles written about AIDE are part of the context for the AI. This article is about how to write requirements as a prompt…
Prompt Engineering for AIDE (opens on the source site)
This article was AI-generated using this project as context. AIDE Project. The purpose of this project is to see how much an AI could generate given enough context, and in this project, all the "source" code is generated using the requirements and unit tests as context. This follows the Next-Level Development: Harnessing AI with AIDE approach. The main parts are: Requirements Documents in .adoc format. JUnit tests in Java. AIDE itself. AI-generated code in Java. Even the articles written about AIDE are part of the context for the AI. This article is about how to write requirements as a prompt…
What might an AI System Prompt look like? (opens on the source site)
Not surprisingly, the system prompts for “o1” are restricted, but it can provide a hypothetical answer. Understanding the Role of System Prompts System prompts serve as the invisible backbone of an AI’s reasoning process. They define core objectives, ethical boundaries, and operational tactics well before the user asks a question. In older models, these prompts were often implicit or underspecified, leaving the AI uncertain about handling ambiguous instructions or potentially unsafe requests. Hypothetical System Prompts for o2 The system prompts for a hypothetical next-generation O2…
What might an AI System Prompt look like? (opens on the source site)
Not surprisingly, the system prompts for “o1” are restricted, but it can provide a hypothetical answer. Understanding the Role of System Prompts System prompts serve as the invisible backbone of an AI’s reasoning process. They define core objectives, ethical boundaries, and operational tactics well before the user asks a question. In older models, these prompts were often implicit or underspecified, leaving the AI uncertain about handling ambiguous instructions or potentially unsafe requests. Hypothetical System Prompts for o2 The system prompts for a hypothetical next-generation O2…
Related topics
This page is generated automatically from the engineering blogs we follow. Every post links to its source, where it was published. See all sources.