General

What Sets the Best Autonomous Coding Agents Apart?

Published Jun 3, 2025

Updated Jun 3, 2025

4 min read

Must-have Features of Coding Agents

Autonomous coding agents are no longer experimental, they are becoming an integral part of modern development workflows, redefining how software is built and maintained. As models become more capable, agents have become easier to produce, leading to an explosion of options with varying depth and utility. Drawing insights from our experience using many agents, let's delve into the features that you'll absolutely want to get the best results.

1. Customizable System Prompts

Custom agent modes, or roles, allow engineers to tailor the outputs to the desired results of their task. For instance, an agent can be set to operate in a "planning mode" focused on outlining development steps and gathering requirements, a "coding mode" optimized for generating and testing code, or a "documentation mode" emphasizing clarity and completeness of written artifacts. You might start with the off-the-shelf planning prompt, but you'll quickly want your own tailored version. Regardless of which modes are included out of the box, the ability to customize and extend them is critical. Agents must adapt to your unique workflows and prioritize what's important to your project. Without this flexibility, even well-designed defaults can fall short in real-world use.

Engineers have preferences, and projects contain existing work. The best agents offer ways to communicate these preferences and decisions effectively. For example, 'pnpm' instead of 'npm' for package management, requiring the agent to seek root causes rather than offer temporary workarounds, or mandating that tests and linting must pass before a task is marked complete. Rules are a layer of control to accomplish this. Rules reinforce technical standards but also shape agent behavior to reflect project priorities and cultural norms. They inform the agent across contexts, think constraints, preferences, or directives that apply regardless of the task. Rules can encode things like style guidelines, risk tolerances, or communication boundaries. By shaping how the agent reasons and responds, rules ensure consistent alignment with desired outcomes.

Roo code is an agent that makes great use of custom modes, and rules are ubiquitous across coding agents. These features form a meta-agent framework that allows engineers to construct the most effective agent for their unique project and workflow details.

2. Usage-based Pricing

The best agents provide as much relevant information as possible to the model. They give transparency and control over what information is sent. This allows engineers to leverage their knowledge of the project to improve results. Being liberal with relevant information to the models is more expensive however, it also significantly improves results.

The pricing model of some agents prioritizes fixed, predictable costs that include model fees. This creates an incentive to minimize the amount of information sent to the model in order to control costs. To get the most out of these tools, you’ve got to get the most out of models, which typically implies usage-based pricing.

3. Autonomous Workflows

The way we accomplish work has phases. For example, creating tests and then making them pass, creating diagrams or plans, or reviewing work before submitting PRs. The best agents have mechanisms to facilitate these phases in an autonomous way. For the best results, each phase should have full use of a context window without watering down the main session's context. This should leverage your custom modes, which excel at each phase of your workflow.

4. Working in the Background

The best agents are more effective at producing desired results and thus are able to be more autonomous. As agents become more autonomous, the ability to work in the background or work on multiple tasks at once becomes increasingly necessary to unlock their full potential. Agents that leverage local or cloud containers to perform work independently of IDEs or working copies on an engineer's machine further increase their utility. This allows engineers to focus on drafting plans and reviewing proposed changes, ultimately to work toward managing multiple tasks at once, overseeing their agent-powered workflows as if guiding a team.

5. Integrations with your Tools

The Model Context Protocol (MCP) serves as a standardized interface, allowing agents to interact with your tools and data sources. The best agents seamlessly integrate with the platforms that engineers rely on, such as Confluence for documentation, Jira for tasks, and GitHub for source control and pull requests. These integrations ensure the agent can participate meaningfully across the full software development lifecycle.

6. Support for Multiple Model Providers

Reliance on a single AI provider can be limiting. Top-tier agents support multiple providers, allowing teams to choose the best models for specific tasks. This flexibility enhances performance, the ability to use the latest and greatest, and also safeguards against potential downtimes or vendor-specific issues.

Final Thoughts

Selecting the right autonomous coding agent is a strategic decision. By prioritizing the features mentioned, technology leaders can adopt agents that can be tuned for their team's success. Tuning agents to projects and teams takes time, as does configuring the plumbing to integrate well with other systems. However, unlocking massive productivity gains is worth the squeeze. Models will become better and better, and the best agents capitalize on these improvements with little to no added effort. Set your organization and teams up to tap into the power of AI-enhanced engineering, and be more effective and more competitive.

This Dot is a consultancy dedicated to guiding companies through their modernization and digital transformation journeys. Specializing in replatforming, modernizing, and launching new initiatives, we stand out by taking true ownership of your engineering projects.

We love helping teams with projects that have missed their deadlines or helping keep your strategic digital initiatives on course. Check out our case studies and our clients that trust us with their engineering.

About the author(s)

Elliott Fouts

“ChatGPT knows me pretty well… but it drew me as a white man with a man bun.” – Angie Jones on AI Bias, DevRel, and Block’s new open source AI agent “goose”

Angie Jones is a veteran innovator, educator, and inventor with over twenty years of industry experience and twenty-seven digital technology patents both domestically and internationally. As the VP of Developer Relations at Block, she facilitates developer training and enablement, delivering tools for developer users and open source contributors. However, her educational work doesn’t end with her day job. She is also a contributor to multiple books examining the intersection of technology and career, including *DevOps: Implementing Cultural Change*, and *97 Things Every Java Programmer Should Know*, and is an active speaker in the global developer conference circuit. With the release of Block’s new open source AI agent “goose”, Angie drives conversations around AI’s role in developer productivity, ethical practices, and the application of intelligent tooling. We had the chance to talk with her about the evolution of DevRel, what makes a great leader, emergent data governance practices, women who are crushing it right now in the industry, and more: Developer Advocacy is Mainstream A decade ago, Developer Relations (DevRel) wasn’t the established field it is today. It was often called Developer Evangelism, and fewer companies saw the value in having engineers speak directly to other engineers. > “Developer Relations was more of a niche space. It’s become much more mainstream these days with pretty much every developer-focused company realizing that the best way to reach developers is with their peers.” That shift has opened up more opportunities for engineers who enjoy teaching, community-building, and breaking down complex technical concepts. But because DevRel straddles multiple functions, its place within an organization remains up for debate—should it sit within Engineering, Product, Marketing, or even its own department? There’s no single answer, but its cross-functional nature makes it a crucial bridge between technical teams and the developers they serve. Leadership Is Not an Extension of Engineering Excellence Most engineers assume that excelling as an IC is enough to prepare them for leadership, but Angie warns that this is a common misconception. She’s seen firsthand how technical skills don’t always equate to strong leadership abilities—we’ve all worked under leaders who made us wonder *how they got there*. When she was promoted into leadership, Angie was determined not to become one of those leaders: > “This required humility. Acknowledging that while I was an expert in one area, I was a novice in another.” Instead of assuming leadership would come naturally, she took a deliberate approach to learning—taking courses, reading books, and working with executive coaches to build leadership skills the right way. Goose: An Open Source AI Assistant That Works for You At Block, Angie is working on a tool called goose, an open-source AI agent that runs locally on your machine. Unlike many AI assistants that are locked into specific platforms, goose is designed to be fully customizable: > “You can use your LLM of choice and integrate it with any API through the Model Context Protocol (MCP).” That flexibility means goose can be tailored to fit developers’ workflows. Angie gives an example of what this looks like in action: > “Goose, take this Figma file and build out all of the components for it. Check them into a new GitHub repo called @org/design-components and send a message to the #design channel in Slack informing them of the changes.” And just like that, it’s done— no manual intervention required. The Future of Data Governance As AI adoption accelerates, data governance has become a top priority for companies. Strong governance requires clear policies, security measures, and accountability. Angie points out that organizations are already making moves in this space: > “Cisco recently launched a product called AI Defense to help organizations enhance their data governance frameworks and ensure that AI deployments align with established data policies and compliance requirements.” According to Angie, in the next five years, we can expect more structured frameworks around AI data usage, especially as businesses navigate privacy concerns and regulatory compliance. Bias in AI Career Tools: Helping or Hurting? AI-powered resume screeners and promotion predictors are becoming more common in hiring, but are they helping or hurting underrepresented groups? Angie’s own experience with AI bias was eye-opening: > “I use ChatGPT every day. It knows me pretty well. I asked it to draw a picture of what it thinks my current life looks like, and it drew me as a white male (with a man bun).” When she called it out, the AI responded: > “No, I don’t picture you that way at all, but it sounds like the illustration might’ve leaned into the tech stereotype aesthetic a little too much.” This illustrates a bigger problem— AI often reflects human biases at scale. However, there are emerging solutions, such as identity masking, which removes names, race, and gender markers so that only skills are evaluated. > “In scenarios like this, minorities are given a fairer shot.” It’s a step toward a more equitable hiring process, but it also surfaces the need for constant vigilance in AI development to prevent harmful biases. Women at the Forefront of AI Innovation While AI is reshaping nearly every industry, women are playing a leading role in its development. Angie highlights several technologists: > “I’m so proud to see women are already at the forefront of AI innovation. I see amazing women leading AI research, training, and development such as Mira Murati, Timnit Gebru, Joelle Pineau, Meredith Whittaker, and even Block’s own VP of Data & AI, Jackie Brosamer.” These women are influencing not just the technical advancements in AI but also the ethical considerations that come with it. Connect with Angie Angie Jones is an undeniable pillar of the online JavaScript community, and it isn’t hard to connect with her! You can find Angie on X (Twitter), Linkedin, or on her personal site (where you can also access her free Linkedin Courses). Learn more about goose by Block. Sticker Illustration by Jacob Ashley...

Mar 13, 2025

4 mins

DevRelEngineering LeadershipAI

“Recognize leadership behavior early. Sometimes people don’t even realize it in themselves…” Kelly Vaughn on Product Leadership, Creating Pathways for Women in Tech, & Conferences

Some leaders build products. Some lead engineering teams. Kelly Vaughn is doing both. As Director of Engineering at Spot AI—a company building video intelligence software—Kelly recently expanded her role to oversee both Product and Engineering for their VMS offering. That shift means juggling strategy, execution, and team development, all while helping others step confidently into leadership themselves. And yes, she still finds time to speak at conferences and answer DMs from people navigating the same transitions she once did. We spoke with Kelly about spotting leadership potential early, why ambiguity doesn’t have to feel chaotic, and the lesson she learned the hard way about managing up. Stepping into Product Leadership Kelly’s new title might look like a promotion on paper, but the shift is more philosophical than anything. > “Engineering leadership is about execution,” she says. “Product leadership is about defining why we’re building something in the first place.” Now leading Product and Engineering for Spot AI’s VMS product, she’s talking to customers, researching market trends, and making smart bets on where to invest next. It’s a role she’s clearly energized by. > “I’m really looking forward to dedicating time to shaping our product’s future.” Thriving in Ambiguity Some people panic when problems are fuzzy or undefined. Others use it as fuel. > “There are two key traits I see in people who handle ambiguity well,” Kelly says. “They stay calm under stress, and they know how to form a hypothesis from a vague problem statement.” That means asking the right questions, taking action quickly, and being totally okay with pivoting when something doesn’t pan out. It’s no surprise that these same traits overlap with great product thinking—a mindset she’s now leaning into more than ever. > “I do some of my best work when navigating uncertainty,” she adds. Read Kelly’s blog on embracing ambiguity in Product! Creating Leadership Pathways for Women in Tech When asked how leaders can create more leadership pathways for women in software engineering, Kelly stressed that it is not a passive process. > “Senior leaders need to be proactive,” Kelly says. “That starts with identifying and addressing bias across hiring, promotions, and day-to-day interactions.” She emphasizes psychological safety—so women feel confident advocating for themselves and others. But she also knows not everyone feels ready to raise their hand. > “Don’t wait for someone to ask for a title change or a growth opportunity. Recognize leadership behavior early. Sometimes people don’t even realize it in themselves yet.” On Stage, In Real Life Kelly’s no stranger to the tech conference circuit—often giving talks on engineering leadership and team growth. Her biggest source of inspiration? Conversations with people trying to make the leap into leadership. > “I might use the same slide deck at three conferences,” she says, “but the talk itself will be different every time.” Rather than sticking to a script, she likes to share recent examples from her own work, tailoring the delivery to the audience in front of her. It keeps things relevant, grounded, and never too polished. Between setting product strategy, mentoring the next generation of leaders, and hopping from one tech conference to the next, Kelly Vaughn is showing what it means to lead with clarity—even when things are unclear. She’s not here to tell you it’s easy. But she will tell you it’s worth it. Connect with Kelly Vaughn on Bluesky. Sign up for Kelly Vaughn’s Newsletter! Sticker Illustration by Jacob Ashley....

Apr 4, 2025

3 mins

Engineering LeadershipSoftware EngineeringAI

Introduction to Vercel’s Flags SDK

Introduction to Vercel’s Flags SDK In this blog, we will dig into Vercel’s Flags SDK. We'll explore how it works, highlight its key capabilities, and discuss best practices to get the most out of it. You'll also understand why you might prefer this tool over other feature flag solutions out there. And, despite its strong integration with Next.js, this SDK isn't limited to just one framework—it's fully compatible with React and SvelteKit. We'll use Next.js for examples, but feel free to follow along with the framework of your choice. Why should I use it? You might wonder, "Why should I care about yet another feature flag library?" Unlike some other solutions, Vercel's Flags SDK offers unique, practical features. It offers simplicity, flexibility, and smart patterns to help you manage feature flags quickly and efficiently. It’s simple Let's start with a basic example: ` This might look simple — and it is! — but it showcases some important features. Notice how easily we can define and call our flag without repeatedly passing context or configuration. Many other SDKs require passing the flag's name and context every single time you check a flag, like this: ` This can become tedious and error-prone, as you might accidentally use different contexts throughout your app. With the Flags SDK, you define everything once upfront, keeping things consistent across your entire application. By "context", I mean the data needed to evaluate the flag, like user details or environment settings. We'll get into more detail shortly. It’s flexible Vercel’s Flags SDK is also flexible. You can integrate it with other popular feature flag providers like LaunchDarkly or Statsig using built-in adapters. And if the provider you want to use isn’t supported yet, you can easily create your own custom adapter. While we'll use Next.js for demonstration, remember that the SDK works just as well with React or SvelteKit. Latency solutions Feature flags require definitions and context evaluations to determine their values — imagine checking conditions like, "Is the user ID equal to 12?" Typically, these evaluations involve fetching necessary information from a server, which can introduce latency. These evaluations happen through two primary functions: identify and decide. The identify function gathers the context needed for evaluation, and this context is then passed as an argument named entities to the decide function. Let's revisit our earlier example to see this clearly: ` You could add a custom evaluation context when reading a feature flag, but it’s not the best practice, and it’s not usually recommended. Using Edge Config When loading our flags, normally, these definitions and evaluation contexts get bootstrapped by making a network request and then opening a web socket listening to changes on the server. The problem is that if you do this in Serverless Functions with a short lifespan, you would need to bootstrap the definitions not just once but multiple times, which could cause latency issues. To handle latency efficiently, especially in short-lived Serverless Functions, you can use Edge Config. Edge Config stores flag definitions at the Edge, allowing super-fast retrieval via Edge Middleware or Serverless Functions, significantly reducing latency. Cookies For more complex contexts requiring network requests, avoid doing these requests directly in Edge Middleware or CDNs, as this can drastically increase latency. Edge Middleware and CDNs are fast because they avoid making network requests to the origin server. Depending on the end user’s location, accessing a distant origin can introduce significant latency. For example, a user in Tokyo might need to connect to a server in the US before the page can load. Instead, a good pattern that the Flags SDK offers us to avoid this is cookies. You could use cookies to store context data. The browser automatically sends cookies with each request in a standard format, providing consistent (no matter if you are in Edge Middleware, App Router or Page Router), low-latency access to evaluation context data: ` You can also encrypt or sign cookies for additional security from the client side. Dedupe Dedupe helps you cache function results to prevent redundant evaluations. If multiple flags rely on a common context method, like checking a user's region, Dedupe ensures the method executes only once per runtime, regardless of how many times it's invoked. Additionally, similar to cookies, the Flags SDK standardizes headers, allowing easy access to them. Let's illustrate this with the following example: ` Server-side patterns for static pages You can use feature flags on the client side, but that will lead to unnecessary loaders/skeletons or layout shifts, which are never that great. Of course, it brings benefits, like static rendering. To maintain static rendering benefits while using server-side flags, the SDK provides a method called precompute. Precompute Precompute lets you decide which page version to display based on feature flags and then we can cache that page to statically render it. You can precompute flag combinations in Middleware or Route Handlers: ` Next, inside a middleware (or route handler), we will precompute these flags and create static pages per each combination of them. ` The user will never notice this because, as we use “rewrite”, they will only see the original URL. Now, on our page, we “invoke” our flags, sending the code from the params: ` By sending our code, we are not really invoking the flag again but getting the value right away. Our middleware is deciding which variation of our pages to display to the user. Finally, after rendering our page, we can enable Incremental Static Regeneration (ISR). ISR allows us to cache the page and serve it statically for subsequent user requests: ` Using precompute is particularly beneficial when enabling ISR for pages that depend on flags whose values cannot be determined at build time. Headers, geo, etc., we can’t know their value at build, so we use precompute() so the Edge can evaluate it on the fly. In these cases, we rely on Middleware to dynamically determine the flag values, generate the HTML content once, and then cache it. At build time, we simply create an initial HTML shell. Generate Permutations If we prefer to generate static pages at build-time instead of runtime, we can use the generatePermutations function from the Flags SDK. This method enables us to pre-generate static pages with different combinations of flags at build time. It's especially useful when the flag values are known beforehand. For example, scenarios involving A/B testing and a marketing site with a single on/off banner flag are ideal use cases. ` ` Conclusion Vercel’s Flags SDK stands out as a powerful yet straightforward solution for managing feature flags efficiently. With its ease of use, remarkable flexibility, and effective patterns for reducing latency, this SDK streamlines the development process and enhances your app’s performance. Whether you're building a Next.js, React, or SvelteKit application, the Flags SDK provides intuitive tools that keep your application consistent, responsive, and maintainable. Give it a try, and see firsthand how it can simplify your feature management workflow!...

May 23, 2025

5 mins

Vercel

Let's innovate together!

We're ready to be your trusted technical partners in your digital innovation journey.

Whether it's modernization or custom software solutions, our team of experts can guide you through best practices and how to build scalable, performant software that lasts.

What Sets the Best Autonomous Coding Agents Apart?

Must-have Features of Coding Agents

1. Customizable System Prompts

2. Usage-based Pricing

3. Autonomous Workflows

4. Working in the Background

5. Integrations with your Tools

6. Support for Multiple Model Providers

Final Thoughts

Elliott Fouts

You might also like

“ChatGPT knows me pretty well… but it drew me as a white man with a man bun.” – Angie Jones on AI Bias, DevRel, and Block’s new open source AI agent “goose”

“Recognize leadership behavior early. Sometimes people don’t even realize it in themselves…” Kelly Vaughn on Product Leadership, Creating Pathways for Women in Tech, & Conferences

Introduction to Vercel’s Flags SDK

Let's innovate together!

You might also like

“ChatGPT knows me pretty well… but it drew me as a white man with a man bun.” – Angie Jones on AI Bias, DevRel, and Block’s new open source AI agent “goose”

“Recognize leadership behavior early. Sometimes people don’t even realize it in themselves…” Kelly Vaughn on Product Leadership, Creating Pathways for Women in Tech, & Conferences

Introduction to Vercel’s Flags SDK