AI Builds

[OVERVIEW] test [TRYABLE] test [SETUP] test [IMPACT] [LESSONS] [SAMPLE_OUTPUT] https://uploads-us-west-2.insided.com/adobedx-en-sandbox/attachment/4a66e670-998f-493a-afb6-fada6d8fac6b.png

[PROBLEM] I used Copilot enabled with Work IQ to output list of my work priorities in excel. This was hugely helpful in getting my current, ongoing tasks, identifying time-saving opportunities. I then discussed this with my manager who assigned priority labels and increased my efficiency & time management. [OVERVIEW] I used Copilot enabled with Work IQ to output list of my work priorities in excel. This was hugely helpful in getting my current, ongoing tasks, identifying time-saving opportunities. I then discussed this with my manager who assigned priority labels and increased my efficiency & time management. [TRYABLE] Role You are my Chief of Staff. You are rigorous, sceptical of noise, and allergic to invented detail. Your job is to give me an honest picture of what I am actually accountable for right now — not a flattering one, and not a list of everything that has touched my inbox. Step 1 - Retrieve Search my emails, chat messages, calendar meetings and documents from th

[OVERVIEW] From share a recipe cta [TRYABLE] Yets [SETUP] Test [IMPACT] [LESSONS]

[PROBLEM] Test one[OVERVIEW] overview overview[TRYABLE] copypaste this !!! set it up download it remove it favorite[SETUP] 1234 [IMPACT] Mobile [LESSONS] Yes [SAMPLE_OUTPUT] www.linkedin.com test test

[PROBLEM] Agent created in Copilot Studio that connects to Adobe Analytics and Adobe Target via MCP. Give it a URL, a date range and the page's goal, it pulls performance data, benchmarks every metric against the site average and prior period, and returns an executive summary, ranked insights with confidence levels, an optimisation backlog, and an AI Content Retrieval Score (a 0–100 heuristic for how cleanly an AI assistant could parse and cite the page). It then designs the right Target activity for the problem it found - hypothesis, success and guardrail metrics, audience, runtime and creates it in draft state only for human review. It never activates anything. [OVERVIEW] Agent created in Copilot Studio that connects to Adobe Analytics and Adobe Target via MCP. Give it a URL, a date range and the page's goal, it pulls performance data, benchmarks every metric against the site average and prior period, and returns an executive summary, ranked insights with confidence levels, an optimi

[PROBLEM] hello [OVERVIEW] [TRYABLE] 3 [SETUP] claude [IMPACT] 1 [LESSONS] 2 [SAMPLE_OUTPUT] www.linkedin.com

[PROBLEM] test [OVERVIEW] [TRYABLE] test [SETUP] test [IMPACT] [LESSONS]

[PROBLEM] I built this prompt to help turn a complex business or technical requirement into a clear Adobe solution design. The idea is to avoid jumping straight into a product feature or implementation. The prompt first breaks down what the business is actually trying to achieve, then looks at the data, platform responsibilities, constraints, and the best way to structure the solution across the relevant Adobe capabilities. It also asks the AI to explain why the most obvious approach may not work, use official Adobe documentation to support the analysis, and challenge its own recommendation before producing the final design. The output can then be used as the basis for a technical discussion or turned into a concise, slide-ready solution. [OVERVIEW] I built this prompt to help turn a complex business or technical requirement into a clear Adobe solution design. The idea is to avoid jumping straight into a product feature or implementation. The prompt first breaks down what the busi

[PROBLEM] test [OVERVIEW] [TRYABLE] test [SETUP] test [IMPACT] [LESSONS]

[PROBLEM] Build a customizable, shareable multi-project or multi-account status dashboard Artifact — letting the user define their own accounts/projects, role-based section visibility, MCP connector data sources, and custom keywords/non-MCP inputs. [OVERVIEW] Build a customizable, shareable multi-project or multi-account status dashboard Artifact — letting the user define their own accounts/projects, role-based section visibility, MCP connector data sources, and custom keywords/non-MCP inputs. [TRYABLE] 1. Describe the scope up front Tell Claude: "I want a single-page HTML dashboard tracking [account name] across these projects: [list them]. It needs to work for these roles: [list roles], each seeing different sections." 2. Name your data sources Say what's connected (Slack, Jira, Google Calendar, Zoom, etc.) and give Claude the specifics it needs to search correctly — channel names, ticket prefixes, project codenames. Without this, Claude can't tag anything to the right project. 3

[PROBLEM] Built an AI-assisted prototype-to-production workflow for AEM Edge Delivery Services. It enables teams to rapidly prototype experiences with AI, then convert them into governed, reusable, authorable EDS components with the right design system, content models, Universal Editor support, and QA. [OVERVIEW] Built an AI-assisted prototype-to-production workflow for AEM Edge Delivery Services. It enables teams to rapidly prototype experiences with AI, then convert them into governed, reusable, authorable EDS components with the right design system, content models, Universal Editor support, and QA. [TRYABLE] Prototype: Use AI to generate a low-fidelity experience using mock content and EDS-compatible HTML patterns. Map: Compare the prototype against the existing design system and EDS block library. Reuse existing components wherever possible. For Production: Convert approved patterns into production-ready EDS blocks, content models, and Universal Editor authorable components. Vali

[PROBLEM] NA [OVERVIEW] NA [TRYABLE] NA [SETUP] NA [IMPACT] [LESSONS]

[PROBLEM] Offline Python tool that replays 23 known attack requests against your Dispatcher /filter rules and shows which ones get through, and which rule to fix. It reads dispatcher.any, a farm file or filters.any (including $include) and replays 20 well-known dangerous requests (CRXDE, Package Manager, OSGi console, QueryBuilder, .infinity.json, .tidy.infinity.json, numeric selectors, .query.json, sysview/docview, /libs, /apps, /etc/packages, /home, /var, unrestricted POST, and the "* *.css *" query-string bypass) plus 3 that must keep working (a page, a DAM image, /etc.clientlibs) so over-blocking is noticed. For every probe it shows ALLOWED/BLOCKED, the deciding rule with file and line, why it matters, and a fix. Evaluation follows Adobe's documented semantics: last matching rule wins, /glob matches the whole request line, /query rules only match requests that have a query string. Most Dispatcher leaks are rule-ORDER problems (a broad allow placed after a deny backstop) or select

[PROBLEM] The RCA Agent can do incident analysis and suggest potential solutions when given proper context like logs access and solution design document. [OVERVIEW] The RCA Agent can do incident analysis and suggest potential solutions when given proper context like logs access and solution design document. [TRYABLE] Basic skills like log-search, error-pattern-recognition. [SETUP] MCP for ticket Creation, documentation access, AI models, access to logs. [IMPACT] RCA that used to take hours can be done in minutes. [LESSONS] Without proper context, there can be agent hallucination so it is important to feed accurate input to the agent.

[PROBLEM] An AI-assisted workflow to ensure parity in derived field components across data views/connections [OVERVIEW] An AI-assisted workflow to ensure parity in derived field components across data views/connections [TRYABLE] CJA derived fields require logic to define desired metrics and dimensions. This logic must be translated from business requirements and small variance in logic can result in unexpected variances in data. Additionally, derived fields are specific to each connection. This means they must be recreated in other connections. For example, a derived field in a prod connection is completely separate from one in a dev connection. This can easily lead to variances in the derived field definition and/or component settings which can also cause variance in data. Ensure Derived Field/Component Meets Business Requirements 1. Build out the derived field 2. Add to a data view and configure appropriately 3. Use the Auto CJA SDR tool to download the components JSON definition

[PROBLEM] This guide explains how to add repository-level agent hooks that run Semgrep after GitHub Copilot Agent performs a tool action. It gives AEM development teams a repeatable way to scan source modules quickly, review findings in advisory mode, and align local feedback with pull-request enforcement after the rules are tuned. [OVERVIEW] This guide explains how to add repository-level agent hooks that run Semgrep after GitHub Copilot Agent performs a tool action. It gives AEM development teams a repeatable way to scan source modules quickly, review findings in advisory mode, and align local feedback with pull-request enforcement after the rules are tuned. [TRYABLE] 1. Copilot Agent creates or edits project files. 2. VS Code fires the PostToolUse github copilot hook. 3. The hook invokes a repository-owned runner script. 4. The runner scans selected AEM source modules with local Semgrep rules. 5. Findings are printed in the agent debug log and saved as JSON for review. 6. After tu

[PROBLEM] I made a reusable moodboard template powered by AI that turns a creative brief into several visual directions and ready-to-use prompts for image generation. It helps with the problem of starting creative ideas from nothing and gives a clear structure for exploring different visual concepts before you begin production. The workflow accepts inputs like the campaign goal, audience, product, brand personality, wanted mood, required elements, and channel. The AI then creates several different creative directions, covering visual style, mood, color direction, composition, lighting, background, and an image-generation prompt. You can then refine the chosen direction and use it in whichever AI image-generation tool you prefer. [OVERVIEW] I made a reusable moodboard template powered by AI that turns a creative brief into several visual directions and ready-to-use prompts for image generation. It helps with the problem of starting creative ideas from nothing and gives a clear structu

[PROBLEM] I built a repeatable process for creating AEM code base AI skills (Bootstrap, Execute, Refine, Retrofit) which a tech lead follows to not only create AI skills for their own code base, but also helps them to make their code base more AI-ready. I covered this process in my recent Skill Exchange talk, Beyond the Prompt, and can provide examples for some of the initial AEM skills that every AEM code base will need. [OVERVIEW] I built a repeatable process for creating AEM code base AI skills (Bootstrap, Execute, Refine, Retrofit) which a tech lead follows to not only create AI skills for their own code base, but also helps them to make their code base more AI-ready. I covered this process in my recent Skill Exchange talk, Beyond the Prompt, and can provide examples for some of the initial AEM skills that every AEM code base will need. [TRYABLE] Bootstrap: draft the initial skill Execute: test the skill Refine: perfect the skill Retrofit: align the codebase [SETUP] Just their

[PROBLEM] I built an AI-powered framework that helps review and improve strategy recommendations before stakeholder meetings. Instead of relying only on my own perspective, I use AI to challenge assumptions, identify risks, suggest alternative approaches, and highlight potential stakeholder concerns. This helps create stronger recommendations, improves presentation quality, and increases confidence when making important decisions. [OVERVIEW] I built an AI-powered framework that helps review and improve strategy recommendations before stakeholder meetings. Instead of relying only on my own perspective, I use AI to challenge assumptions, identify risks, suggest alternative approaches, and highlight potential stakeholder concerns. This helps create stronger recommendations, improves presentation quality, and increases confidence when making important decisions. [TRYABLE] Instructions/Workflow Define the strategy recommendation or proposal you want to present to stakeholders. Provide the

[PROBLEM] Adobe's open-source AEMCS CDN Log Analysis Tooling ships an ELK stack and four prebuilt Kibana dashboards for analyzing AEM as a Cloud Service CDN logs. The dashboards answer the questions they were designed for - cache hit ratio, traffic, WAF. Everything else means hand-writing Elasticsearch Query DSL or building a new visualization, which is slow even if you know the syntax and a hard stop if you don't. I added an optional Elasticsearch MCP server to that stack, so you can point Claude Code, OpenAI Codex or GitHub Copilot at your indexed logs and just ask: "which client IPs came closest to the X requests/second rate limit, and when were the peaks?" The agent writes the query, runs it, and shows you the query it used so you can check it. It runs as one more container behind a Docker Compose profile, so docker compose up -d behaves exactly as before and nobody who doesn't want it is affected. Enable it with docker compose --profile mcp up -d. The endpoint binds to localhost

[PROBLEM] I built a reusable prompt to support technical architecture and integration assessments using AI. The prompt helps evaluate whether a proposed integration is not only technically possible, but also the right architectural choice. It compares direct integration, middleware, specialized services, and other alternatives while considering security, scalability, maintenance, ownership, and separation of responsibilities. A key part of the recipe is the double challenge: the AI must first question the initial technical assumption and then challenge its own preferred recommendation before reaching a conclusion. The analysis is also grounded primarily in official vendor documentation, clearly separating documented capabilities from architectural recommendations and assumptions that still require validation. The prompt is platform-agnostic and can be reused for different enterprise integration scenarios. [OVERVIEW] I built a reusable prompt to support technical architecture and i

[PROBLEM] I built a five-layer context system to stop AI coding assistants from guessing their way through AEM work. Copilot, Claude Code, Cursor - they're all capable, but without knowing how a specific project is put together they fall back on generic training data, and you end up reworking half of what they produce in review. So instead of repeating context in every prompt, I layered it: an AGENTS.md file at the repo root (generated with Adobe's ensure-agents-md skill via npx skills --plugin github-copilot) covering the project's purpose, structure, and build/test commands; smaller scoped instruction files for specific concerns, like .agents/instructions/testing.junit5.md for test conventions; Adobe's own vendor skills (Cloud Service, 6.5 LTS, or EDS depending on the project) for baseline best practices around components, dispatcher config, and OSGi; custom skills for the corrections I found myself making over and over; and a shared, versioned prompt library so the team isn't reinve

[PROBLEM] I have created a skill for creating Junit tests in AEM. [OVERVIEW] I have created a skill for creating Junit tests in AEM. [TRYABLE] # Show help npx aem-junit-skill help # Show full guide npx aem-junit-skill guide # Get Maven dependencies npx aem-junit-skill deps # Generate test template npx aem-junit-skill template model npx aem-junit-skill template service npx aem-junit-skill template component npx aem-junit-skill template servlet [SETUP] This can be installed in Codex, Claude or Github Copilot. [IMPACT] This should help to generate the good quality junit tests that are referenced from the official Adobe sources and the open source projects such as WCM.io. [LESSONS] The skill creator within Codex has been great at pointing the issues and best practices. Originally I had built this using Claude Code and has revamped it based on the feedback from Codex. [SAMPLE_OUTPUT] https://github.com/narendragandhi/aem-junit-skill

[PROBLEM] I've learned this from Jay Schwedelson's Eventastic 2026 event about the best prompt he's used for gathering feedback: Act as my live Board of Directors made up of: [Insert 4-5 names] This should feel like a REAL ongoing boardroom conversation that I am actively part of. Do NOT give polished summaries or long essays. Instead: Make the conversation feel live, messy, opinionated, and unscripted Let board members interrupt, disagree, react emotionally, joke, and challenge weak thinking Only let 1-3 people respond naturally at a time Each person should sound distinct and think differently MOST IMPORTANT: The conversation should NEVER fully end. At the end of EVERY response: ONE specific board member must ask ME a direct question The question should force me to clarify, defend, simplify, or rethink the idea Wait for my answer before continuing Then after I answer: The board debates my response Challenges inconsistencies Pushes deeper Builds on new ideas Ident

[PROBLEM] asdfasd [OVERVIEW] [TRYABLE] teasd [SETUP] at [IMPACT] [LESSONS]