Over the past year, I’ve built five projects that put AI into practical web workflows: searching private documents, following up with leads, reviewing code, turning notes into reports, and helping with bookings. The clearest lesson so far is that a useful AI feature needs more than a convincing answer: it needs a way to ground or check that answer, a sensible human handoff, and evaluation that makes its limitations visible.
Five projects, five different jobs for AI
These projects are experiments and portfolio work, not products compared under one test. Each tackles a different task, and the evidence available for each is different: Groundwork has self-reported evaluation scores, while the other descriptions focus on workflow and design.
| Project | Input and task | How the output is handled | Evidence described |
|---|---|---|---|
| Groundwork | Uploaded documents; answer questions about them | Combines keyword and semantic search, reranks results, and returns answers linked to source material | Author-reported Ragas scores; no dataset or run configuration stated |
| LeadAI | New leads that need a response | Drafts and emails follow-ups, then logs leads in Google Sheets through n8n | No measured conversion or business-impact results stated |
| AI CodeReview Pro | Code changes for review | Uses a group of agents; routes risky areas such as authentication and payments to a person rather than automatically approving them | A described safety design; no measured defect reduction stated |
| NotesToReport | Raw notes to be turned into a report | Adds citations and blocks a report when claims do not match the notes, using a stated faithfulness threshold | Author-reported threshold of 0.85; no independent validation described |
| Aurelia Retreat | A booking website | Pairs an AI assistant with a lead dashboard | Functionality is described; no evaluation results stated |
Groundwork: document answers need retrieval and evidence
Groundwork lets users upload documents and ask questions about them. The described retrieval flow combines keyword matching with semantic search, reranks the results, and generates answers that point back to the source material. That source connection matters: it gives a reader a way to inspect what an answer is based on instead of treating generated text as self-validating.
I also ran into an operational issue. I say the free hosting I initially used caused the search index to disappear, so I moved index storage to Qdrant Cloud. That experience is a reminder that a retrieval app depends not only on prompting and models, but also on keeping its index available. I have not published enough deployment detail here to make a broader claim about hosting reliability.
#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
What the reported evaluation does—and doesn’t—show
I report testing Groundwork with Ragas and getting 1.00 for faithfulness and 0.71 for answer relevancy. Those are my reported results, not independently verified benchmarks. The article does not state the evaluation dataset, metric configuration, or run conditions, so the numbers should be read as a snapshot of my own evaluation rather than a score that can be fairly compared with another RAG app.
The gap between the two scores is still useful as a development signal: in my reported run, faithfulness was stronger than answer relevancy, which I identified as the area to improve. A system can stay close to its retrieved material yet still fail to answer the question as directly as a user needs. A score is most helpful when it points to a specific iteration target, and when its evaluation setup is clear enough to interpret.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
LeadAI: automate the follow-up, not the claimed outcome
LeadAI addresses slow responses to new leads. I describe it as drafting and emailing follow-ups, recording leads in Google Sheets, and running the workflow through n8n. This is a practical automation pattern: connect an incoming task to a drafted action and keep a record in a tool the business already uses.
I have not reported conversion gains or another measured business outcome for LeadAI. Automating a follow-up workflow is not, by itself, evidence that more leads convert or that responses are better. Those claims would require outcome data beyond the workflow description.
Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Repair Windows errors before they cause bigger problemsFix Now →Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
AI CodeReview Pro: keep people in the loop for high-risk changes
AI CodeReview Pro uses a group of agents to review code changes. The important design decision is not simply that multiple agents participate; it is that risky areas such as authentication and payments are sent to a person rather than being automatically approved.
That human handoff is a safety boundary, not proof that the tool catches more defects. I have not reported a measured change in defect rates. The project’s useful principle is narrower: when the consequence of a mistaken approval is high, a review workflow can reserve final judgment for a person instead of treating an automated review as authorization.
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
NotesToReport: constrain claims against the source notes
NotesToReport turns raw notes into a report with citations. I say it blocks the report if claims do not match the notes, using a faithfulness threshold of 0.85. This makes the constraint part of the workflow: the intended output is not merely a polished report, but one whose claims are checked against the supplied material.
The 0.85 figure is my stated project threshold, not a universal standard for faithfulness or a validated guarantee that every unsupported claim will be caught. The available description does not establish how the threshold behaves across different notes or report types.
Free tools Windows power users keep installed
One-click scans. No signup required.
Best Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
Aurelia Retreat: adding an assistant to a booking experience
Aurelia Retreat is a booking website with an AI assistant and a lead dashboard. It applies the same broader idea—put an AI interaction inside an ordinary web application—to a customer-facing booking context. The description does not specify evaluation results or establish how the assistant performs with booking questions, so I treat it as a project feature rather than evidence of booking or support outcomes.
What these builds have taught me so far
- Ground answers in inspectable material. Groundwork links answers to document sources, while NotesToReport is designed to cite notes and check claims against them.
- Make evaluation specific to the failure you want to improve. My Groundwork results suggest a distinction between faithfulness and answer relevancy; the metrics are useful as project-level signals, not stand-alone proof of quality.
- Use automation carefully around consequential actions. LeadAI automates follow-up steps, while AI CodeReview Pro sends certain risky code changes to human review.
- Separate a working feature from a demonstrated impact. The project descriptions explain what the tools are intended to do; except for Groundwork’s self-reported scores, they do not provide measured outcomes.
I share these projects as portfolio work and describe taking on freelance AI automation and full-stack work. The project descriptions, demos, and code are presented through my portfolio; I have not independently verified its current availability here.
And if you’ve shipped a RAG app, what did you use to measure whether the answers were good?
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
