Where these 8 reports land
Build it0
Scope it5
Keep it3
Category report
AI Assistant
8 products ranked by how much of their useful core an AI coding agent can reproduce: 0 strong builds, 5 scoped builds, and 3 weak replacements.
How the score breaks down here
- Interface
- 54
- Core workflow
- 51
- Data access
- 48
- Operations
- 39
- Trust & safety
- 49
50/100 average buildability
Why people keep paying here
- execution polish5 of 8 reports
The last 20 percent is sync, migration fidelity, speed, and edge cases.
- integrations5 of 8 reports
Connectors, OAuth flows, and vendor API changes require constant upkeep.
- proprietary models3 of 8 reports
Model quality and inference operations are part of the product.
The typical achievable core in this category: answer from retrieval over your own notes and files, with sources visible.
Scope it
Admix
A local chat UI with side-by-side replies is a contained project when it calls OpenRouter, but Admix's value depends on access to many hosted models, a current catalog, provider routing, and a maintained account and billing layer. You can reproduce the comparison workflow. You cannot reproduce the model access and service layer for a flat $10 subscription.
Scope it
Yaps
Kinda. A coding agent can one-shot an isolated Yaps feature, such as hotkey dictation, a Markdown notes shell, or local read-aloud, but not the integrated product. Yaps spans native work across macOS, Windows, Linux, Android, and iOS, with platform-level text insertion and mobile keyboards, local AI model orchestration, notes and cross-device sync, browser capture, transcription and diarization, speech and media tools, permissions, installers, updates, and long-tail reliability. The honest DIY outcome is a useful single-platform subset, not a replacement for the suite.
Scope it
Littlebird
Public detail on this one is thin, so treat this entry as a first pass rather than a teardown. Anything in the "AI assistant that reads and drafts for you" shape is mostly a wrapper: a model API, a place to put your context, and a loop that runs on a schedule. A coding agent can rebuild that shape with a focused implementation and you keep the API bill instead of the subscription. What you will not rebuild with a focused implementation is the polish, the mobile surface, and whatever integrations the paid product ships against your actual accounts. Verdict stays "kinda" until someone confirms whether the real value here is the agent loop or the connectors underneath it.
Scope it
Cluely
The core loop is genuinely thin: capture a screenshot, transcribe the mic, feed both to a multimodal model, stream the answer into a transparent always-on-top window on a hotkey. An agent gets that working in a session, and it will feel uncomfortably close to the demo. The gaps are the unglamorous parts: capturing the other side's audio takes virtual audio devices, latency has to beat the conversation, and the headline trick of staying invisible in screen shares depends on fragile platform window flags that vary by OS and conferencing app. Your DIY version will work fine when you are alone with your own screen, and may quietly betray you the one time it matters.
Keep it
ChatGPT
You can build a chat UI over APIs, but you cannot solo-recreate the model, multimodal stack, tools, memory/product layer, safety systems, and scale.
Scope it
BoltAI
A coding agent can one-shot a basic chat window that calls a few AI APIs. That reproduces only a small part of BoltAI. A credible replacement must remain fast with large histories and active streams, combine SwiftUI with purpose-built AppKit components where the framework falls short, and make focus, keyboard navigation, menus, windows, drag and drop, and global shortcuts behave like a real Mac app. It must also reproduce AI Workflows, Instant Chat, Instant Dictation, attachments, tools, provider-specific behavior, local persistence, sync recovery, and protected credentials. These are interacting product systems, not a collection of generated screens.
Keep it
Claude
A Claude-like UI is trivial; the model, safety/reliability layer, long-context performance, artifacts/projects, and platform distribution are not.
Keep it
Google Gemini
A chat UI is easy, but Gemini's model access, Google ecosystem integration, multimodality, storage tie-ins, and platform distribution are not solo-buildable.