Posts by Avneet

@Avneet

Avneet bansalverified

Senior Delivery Consultant, AWS Professional Services · Kubernetes, EKS and Gen...
Orlando, FL avneetbansal-aws.github.io Joined October 2026
2.9k Points • 49 Badges • 19 Connections • 20 Followers • 22 Following

Posts by Avneet

Avneetverified • • in Articles • 11 min read
A normal Lambda function that has to wait pays for the wait. If your workflow extracts a document, then waits five minutes for a confirmation, the function sits there billing for all five minutes, and anything longer than the 15-minute limit does no...
post-cover-35466
Avneetverified • • in Articles • 10 min read
!Image descriptionhttps://dev-to-uploads.s3.us-east-2.amazonaws.com/uploads/articles/c5smdlluse3wn13p9tf1.png For a decade, 900 seconds was the hard wall on a single Lambda invocation. If one continuous computation needed longer, Lambda was the wron...
Avneetverified • • in Articles • 12 min read
🛡️ One Line in a Pod Spec, a VM Underneath: A Practical Guide to AWS Nitro Sandboxes on EKS > TL;DR > - Pods on a node normally share one Linux kernel. A container escape or kernel bug in one pod can reach its neighbors. Nitro Sandboxes give each o...
post-cover-34594
Avneetverified • • in Articles • 8 min read
I recently moved a structured-extraction pipeline from Claude Sonnet 4.6 to Sonnet 5.5 on Amazon Bedrock. On paper it is a model ID change: the same family, a lower price per token, better benchmark scores. In practice, some requests that worked on 4...
post-cover-34578
Avneetverified • • in Articles • 8 min read
Invoices from the field rarely arrive as clean PDFs. They arrive as phone photos: the invoice lying on a stack of other papers, a coffee receipt on top of it, or a sheet held against a car dashboard. I wanted to know which extraction setup holds up i...
post-cover-34113
Avneetverified • • in Articles • 5 min read
🧠 Spatial Memory vs Correction Memory: I Benchmarked Both Against a Plain LLM > TL;DR > - Two open-source memory layers for LLM document extraction, measured on the same 120 synthetic invoices and forms, next to a no-memory baseline, with Claude Ha...
Avneetverified • • in Articles • 2 min read
🤖 From Writing the Spec to Approving It: What AI-DLC Looks Like on a Real Build > TL;DR > - AI-DLC is public and open source: awslabs/aidlc-workflowshttps://github.com/awslabs/aidlc-workflows. The method comes from this AWS DevOps blog posthttps://...
post-cover-33078
Avneetverified • • in Articles • 10 min read
🌐 Organization-Wide EC2 DNS Automation with EventBridge and AWS Config Aggregator: One Rule Per Account > TL;DR > - Detecting EC2 launches and terminations across a whole AWS Organization for DNS is not the five-minute single-account job it looks l...
post-cover-32736
Avneetverified • • in Articles • 6 min read
🛡️ Kubernetes Security Is Three Problems, Not One: Admission, Identity, Runtime > TL;DR > - Most Kubernetes compromises start inside the perimeter, where the firewall verifies nothing. > - Treat security as three independent problems: admission wha...
post-cover-32018
Avneetverified • • in Articles • 9 min read
🛡️ A Field Guide to Beating Amazon Bedrock Throttling > TL;DR > - Know your quota first: check Service Quotas, learn which limits are adjustable soft and which are not hard. > - Retry with exponential backoff and full jitter on throttling errors. T...
post-cover-31889
Avneetverified • • in Articles • 6 min read
🔑 The Bottleneck Was Not the Model. It Was the Prompt Lookup. > TL;DR > - A managed prompt-management service was throttling prompt retrieval on the hot path, which capped the whole pipeline. > - The model was never the bottleneck. Fetching the pro...
post-cover-31651
Avneetverified • • in Articles • 6 min read
🌉 The GitOps Bridge: Keep Terraform and ArgoCD Out of Each Other's Way > TL;DR > - Infrastructure Terraform and applications ArgoCD/Flux have different change frequencies, approval flows, and blast radii. Coupling them is the root problem. > - The ...
post-cover-30765
Avneetverified • • in Articles • 6 min read
🚦 Your Readiness Probe Is Lying to You > TL;DR > - KEDA's Metrics Server reported Ready even when its gRPC connection to the keda-operator was down. > - In that state the HPA silently stops receiving scale signals, while the replica still looks hea...
Avneetverified • • in Articles • 11 min read
🛡️ A Prompt-Injection Firewall for AWS: What I'd Build, and What I Measured > TL;DR > - Prompt injection is OWASP's #1 LLM risk across every edition, and a 2026 proof shows pure input-wrapper defenses face a hard trilemma: they cannot be continuous...
post-cover-30639
Avneetverified • • in Articles • 5 min read
After OCR, most pipelines throw the layout away and re-discover the same form from scratch every time. textract-field-memoryhttps://github.com/aws-samples/sample-textract-field-memory is a small, zero-dependency Python layer that remembers where fiel...
post-cover-30618
Avneetverified • • in Articles • 4 min read
> TL;DR — I open-sourced an AWS sample that makes LLM document extraction learn from human corrections. Each QA fix is captured once and reused, so the pipeline gets more accurate and cheaper over time — with no retraining and no redeployment. Repo: ...
post-cover-30620
Avneetverified • • in Articles • 5 min read
A field survey of the Kubernetes + LLM inference stack in 2026 — the problems that now have serious players, and the edges that are still genuinely underserved. If you run large language models on Kubernetes, you've probably noticed the ground shift...
post-cover-30619
Avneetverified • • in Articles • 7 min read
Most production LLM extraction pipelines route every field through a frontier model, every time. It works, and for a while nobody questions the bill. Then volume grows, or someone runs the per-document math, and the real question shows up. How much o...
post-cover-30616
chevron_left